JP2016180778A - Information processing system and information processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technology which enables voice recognition processing to start according to the situation flexibly.SOLUTION: There is provided an information process system having an output control unit that makes an output unit output conditions for the start of voice recognition processing to be performed by a voice recognition unit for sound information input from a sound collection unit, where the output control unit dynamically changes the conditions for the start of voice recognition processing to be output by the output unit.SELECTED DRAWING: Figure 3

Description

  The present disclosure relates to an information processing system and an information processing method.

  2. Description of the Related Art In recent years, a technique is known in which sound recognition processing is performed on sound information collected by a microphone to obtain a result of the speech recognition processing. The result of the speech recognition process is output in a manner that can be perceived by the user. For example, the voice recognition process for sound information collected by a microphone can be started with a start operation input from the user as a trigger (see, for example, Patent Document 1).

JP 2004-094077 A

  Here, when the condition for starting the speech recognition process for the sound information collected by the microphone is unchanged, it is difficult to start the speech recognition process flexibly according to the situation. Therefore, it is desired to provide a technology that can flexibly start the voice recognition processing according to the situation.

  According to the present disclosure, the output control unit is configured to cause the output unit to output a start condition of a voice recognition process performed by the voice recognition unit on the sound information input from the sound collection unit, and the output control unit includes the output control unit, There is provided an information processing system that dynamically changes the start condition of the voice recognition processing to be output to an output unit.

  According to the present disclosure, the output unit includes outputting a start condition of a voice recognition process performed by the voice recognition unit on the sound information input from the sound collection unit, and causing the output unit to output the sound recognition process. An information processing method including dynamically changing the start condition of the speech recognition process is provided.

  As described above, according to the present disclosure, a technique capable of flexibly starting a voice recognition process according to a situation is provided. Note that the above effects are not necessarily limited, and any of the effects shown in the present specification, or other effects that can be grasped from the present specification, together with or in place of the above effects. May be played.

It is a figure for demonstrating the speech recognition process in a general system. It is a figure showing an example of composition of an information processing system concerning an embodiment of this indication. 3 is a block diagram illustrating a functional configuration example of an information processing system according to an embodiment of the present disclosure. FIG. It is a figure which shows the example of a screen transition until it detects the starting trigger of a speech recognition process from the display of an initial screen. It is a figure which shows the example of the screen transition after the remaining time until a speech recognition process is started as a start condition until a speech recognition process is started. It is a figure which shows the example of a screen transition after the information regarding user operation required in order to start a speech recognition process is output as a start condition until a speech recognition process is started. It is a figure for demonstrating the example which changes start conditions dynamically based on the sound information input from the sound collection part, after the starting trigger of a speech recognition process is detected. It is a figure which shows the example which outputs display information to an output part as start conditions. It is a figure which shows the example which outputs display information to an output part as start conditions. It is a figure which shows the example which outputs audio | voice information to an output part as start conditions. It is a figure which shows the example which outputs audio | voice information to an output part as start conditions. It is a flowchart which shows the example of the flow of the operation | movement which dynamically changes the starting condition output to an output part based on the sound information input from the sound collection part after the starting trigger of a speech recognition process was detected. It is a flowchart which shows the example of the flow of the operation | movement which dynamically changes the starting condition output to an output part based on the sound information input from the sound collection part after the starting trigger of a speech recognition process was detected. The remaining time until the voice recognition process is started is dynamically shortened based on past sound information collected at a predetermined time after the activation trigger is detected in the past until the voice recognition process is started. It is a figure for demonstrating the example to do. The remaining time until the voice recognition process is started is dynamically shortened based on past sound information collected at a predetermined time after the activation trigger is detected in the past until the voice recognition process is started. It is a figure for demonstrating the example to do. The remaining time until the voice recognition process is started is dynamically lengthened based on past sound information collected at a predetermined time after the activation trigger is detected in the past until the voice recognition process is started. It is a figure for demonstrating the example to do. The remaining time until the voice recognition process is started is dynamically lengthened based on past sound information collected at a predetermined time after the activation trigger is detected in the past until the voice recognition process is started. It is a figure for demonstrating the example to do. It is a figure which shows the example of the display information when the remaining time until a speech recognition process is started becomes short. It is a figure which shows the example of the display information when the remaining time until a speech recognition process is started becomes long. Flow of operation for dynamically changing the start condition to be output to the output unit based on past sound information collected in a predetermined time from when the activation trigger is detected in the past to when the voice recognition process is started It is a flowchart which shows the example of. Flow of operation for dynamically changing the start condition to be output to the output unit based on past sound information collected in a predetermined time from when the activation trigger is detected in the past to when the voice recognition process is started It is a flowchart which shows the example of. It is a figure which shows the example of the correspondence of a filler and its audio | voice waveform. It is a figure for demonstrating the example which changes operation | movement by whether the filler is contained in the sound information input from the sound collection part. It is a figure which shows the modification 1 of a structure of an information processing system. It is a figure which shows the modification 2 of a structure of an information processing system. It is a figure which shows the modification 2 of a structure of an information processing system. It is a figure which shows the modification 2 of a structure of an information processing system. It is a figure which shows the modification 2 of a structure of an information processing system. It is a figure which shows the modification 3 of a structure of an information processing system. It is a figure which shows the modification 3 of a structure of an information processing system. It is a figure which shows the modification 3 of a structure of an information processing system. It is a figure which shows the modification 3 of a structure of an information processing system. It is a block diagram which shows the hardware structural example of an information processing system.

  Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In addition, in this specification and drawing, about the component which has the substantially same function structure, duplication description is abbreviate | omitted by attaching | subjecting the same code | symbol.

  In the present specification and drawings, a plurality of components having substantially the same functional configuration may be distinguished by adding different numerals after the same reference numerals. However, when it is not necessary to particularly distinguish each of a plurality of constituent elements having substantially the same functional configuration, only the same reference numerals are given.

The description will be made in the following order.
0. Background 1. Embodiment of the present disclosure 1.1. System configuration example 1.2. Functional configuration example 1.3. Functional details of information processing system 1.4. Modification of system configuration 1.5. 1. Hardware configuration example Conclusion

<0. Background>
First, the background of the embodiment of the present disclosure will be described with reference to the drawings. FIG. 1 is a diagram for explaining speech recognition processing in a general system. In the following description, a voice (voice or speech) and a sound are used separately. Further, the utterance indicates a state in which the user is uttering sound, and the silence indicates a state in which sound information is collected with a volume smaller than the threshold.

  As shown in FIG. 1, a general system (hereinafter also simply referred to as “system”), when an operation for selecting a speech recognition start operation object G14 for starting speech recognition processing is input from a user, Such an operation is detected as an activation trigger for the voice recognition process, and a sound collection start screen G91 is displayed (time T91). When the sound collection start screen G91 is displayed, the user starts speaking (time T92), and the system performs sound recognition processing on the collected sound information while collecting sound with the microphone (S91).

  When the utterance section Ha ends (time T93), a silent state is started. Then, the system detects a section Ma (hereinafter, also referred to as a “silent section”) Ma in which the duration of the sound information collected by the microphone continues and reaches a predetermined target time that is below the reference volume. (Time T94), a predetermined execution operation is executed based on the result of the speech recognition process performed on the sound information collected in the utterance section Ha (S92).

  Here, the execution operation based on the result of the voice recognition process is not particularly limited. For example, the execution operation based on the result of the speech recognition process includes an operation of outputting a search result corresponding to a character string as a result of the speech recognition process, an operation of outputting a character string as a result of the speech recognition process, Any one of an operation of outputting the processing result candidate obtained in the process and an operation of outputting a character string for replying to the utterance content extracted from the character string as a result of the speech recognition process may be included.

  Here, the method of extracting the utterance content from the character string as a result of the speech recognition process is not limited. For example, a technique for extracting utterance contents from a character string as a result of speech recognition processing is performed by performing natural language processing (for example, language analysis, semantic analysis, etc.) on a character string as a result of speech recognition processing. The content may be extracted.

  During the execution operation process, the system displays a screen G92 indicating that the execution operation process is in progress. When the execution operation ends (time T95), the system displays a screen G93 indicating the result of the execution operation. In the example shown in FIG. 1, “collar”, “bid”, and “kick” are included in the screen G93 showing the result of the execution operation as a search result corresponding to the character string as the result of the speech recognition process.

  As described above, in a general system, the voice recognition process is started before the voice recognition process start condition is output. Therefore, when there is a user who considers the utterance content after performing the operation of selecting the voice recognition start operation object G14, the sound information collected before the start of the utterance is also subject to the voice recognition process. The voice recognition process may be affected.

  For example, in the sound information collected before the start of utterance, there may be fillers or extra utterances uttered by the user himself / herself. The filler means a word that is sandwiched between the utterances between the utterances, such as “um”, “that”, “well”. In addition, noise or the like may exist in the sound information collected before the start of utterance. Note that, as described above, noise may mean sound information obtained by excluding a user's voice from sound information input from the sound collection unit 120.

  In addition, the result of the voice recognition process for the sound information collected before the start of the utterance may affect the voice recognition process for the sound information collected after the utterance is started. In addition, when voice recognition processing is performed based on sound information collected before the start of utterance and a silent section is detected before the start of utterance, an execution operation based on the result of the voice recognition processing is started before the start of utterance. There is also a possibility that.

  In view of this, the present specification proposes a technique for outputting a voice recognition process start condition before the voice recognition process is started. Furthermore, if a certain start condition is output regardless of the situation, it is difficult to start the voice recognition process flexibly according to the situation. Therefore, in the present specification, a technique capable of flexibly starting the speech recognition processing according to the situation is proposed.

  The background of the embodiment of the present disclosure has been described above.

<1. Embodiment of the present disclosure>
[1.1. System configuration example]
Next, a configuration example of the information processing system 10 according to the embodiment of the present disclosure will be described with reference to the drawings. FIG. 2 is a diagram illustrating a configuration example of the information processing system 10 according to the embodiment of the present disclosure. As illustrated in FIG. 2, the information processing system 10 according to the embodiment of the present disclosure includes an image input unit 110, an operation input unit 115, a sound collection unit 120, and an output unit 130. The information processing system 10 can perform voice recognition processing on voices uttered by a user U (hereinafter also simply referred to as “user”).

  The image input unit 110 has a function of inputting an image. In the example shown in FIG. 2, the image input unit 110 includes two cameras embedded in the table Tbl. However, the number of cameras included in the image input unit 110 is not particularly limited as long as it is one or more. In such a case, the position where each of the one or more cameras included in the image input unit 110 is provided is not particularly limited. The one or more cameras may include a monocular camera or a stereo camera.

  The operation input unit 115 has a function of inputting a user U operation. In the example shown in FIG. 2, the operation input unit 115 includes one camera suspended from the ceiling that exists above the table Tbl. However, the position where the camera included in the operation input unit 115 is provided is not particularly limited. Further, the camera may include a monocular camera or a stereo camera. Further, the operation input unit 115 may not be a camera as long as it has a function of inputting the operation of the user U. For example, the operation input unit 115 may be a touch panel or a hardware button.

  The output unit 130 has a function of displaying a screen on the table Tbl. In the example illustrated in FIG. 2, the output unit 130 is suspended from the ceiling above the table Tbl. However, the position where the output unit 130 is provided is not particularly limited. Typically, the output unit 130 may be a projector capable of projecting the screen onto the top surface of the table Tbl, but may be another type of display as long as it has a function of displaying the screen. May be.

  In this specification, the case where the top surface of the table Tbl is the display surface of the screen will be mainly described, but the display surface of the screen may be other than the top surface of the table Tbl. For example, the display surface of the screen may be a wall, a building, a floor surface, the ground, or a ceiling. Alternatively, the display surface of the screen may be a non-planar surface such as a curtain fold, or may be a surface in another place. When the output unit 130 has a display surface, the display surface of the screen may be the display surface of the output unit 130.

  The sound collection unit 120 has a function of collecting sound. In the example shown in FIG. 2, the sound collection unit 120 includes a total of six microphones including three microphones existing above the table Tbl and three microphones existing on the upper surface of the table Tbl. However, the number of microphones included in the sound collection unit 120 is not particularly limited as long as it is one or more. In such a case, the position at which each of the one or more microphones included in the sound collection unit 120 is provided is not particularly limited.

  However, if the sound collection unit 120 includes a plurality of microphones, the arrival direction of the sound can be estimated based on sound information collected by each of the plurality of microphones. Further, if the sound collection unit 120 includes a microphone having directivity, the direction of arrival of sound can be estimated based on sound information collected by the microphone having directivity.

  The configuration example of the information processing system 10 according to the embodiment of the present disclosure has been described above.

[1.2. Functional configuration example]
Subsequently, a functional configuration example of the information processing system 10 according to the embodiment of the present disclosure will be described. FIG. 3 is a block diagram illustrating a functional configuration example of the information processing system 10 according to the embodiment of the present disclosure. As illustrated in FIG. 3, the information processing system 10 according to the embodiment of the present disclosure includes an image input unit 110, an operation input unit 115, a sound collection unit 120, an output unit 130, and an information processing device 140 (hereinafter referred to as “information processing device 140”). , Also referred to as “control unit 140”).

  The information processing device 140 executes control of each unit of the information processing system 10. For example, the information processing apparatus 140 generates information output from the output unit 130. Further, for example, the information processing apparatus 140 reflects information input by the image input unit 110, the operation input unit 115, and the sound collection unit 120 in information output from the output unit 130. As illustrated in FIG. 3, the information processing apparatus 140 includes an input image acquisition unit 141, a sound information acquisition unit 142, an operation detection unit 143, a recognition control unit 144, a voice recognition unit 145, and an output control unit 146. With. Details of these functional blocks will be described later.

  Note that the information processing apparatus 140 may be configured by, for example, a CPU (Central Processing Unit). When the information processing device 140 is configured by a processing device such as a CPU, the processing device can be configured by an electronic circuit.

  The function configuration example of the information processing system 10 according to the embodiment of the present disclosure has been described above.

[1.3. Function details of information processing system]
Subsequently, functional details of the information processing system 10 according to the embodiment of the present disclosure will be described. FIG. 4 is a diagram illustrating an example of screen transition from the display of the initial screen to the detection of the activation trigger for the voice recognition process. Referring to FIG. 4, the output control unit 146 displays an initial screen G10-1. The initial screen G10-1 is a recognition field which is a display column for a voice recognition start operation object G14 for starting voice recognition processing, and a character string obtained by the voice recognition processing (hereinafter also referred to as “recognized character string”). A character string display field G11 is included.

  The initial screen G10-1 includes a delete all operation object G12 for deleting all recognized character strings and a confirm operation object G13 for confirming a recognized character string. The initial screen G10-1 includes a forward moving operation object G15 for returning the cursor position in the recognized character string to the front, a backward moving operation object G16 for moving the cursor position in the recognized character string backward, and a character at the cursor position. Alternatively, a delete operation object G17 for deleting a word is included.

  First, as shown in the screen G10-2, when an operation for selecting the voice recognition start operation object G14 by the user is input by the operation input unit 115, the operation is detected by the operation detection unit 143 as a start trigger of the voice recognition processing. (Time T10). When the activation trigger for the speech recognition process is detected, the output control unit 146 outputs a start condition for the speech recognition process. Here, an operation for selecting the speech recognition start operation object G14 will be described as an example as an activation trigger for the speech recognition process, but the activation trigger for the speech recognition process is not limited to such an example.

  For example, the activation trigger for the voice recognition process may be an operation of pressing a hardware button for starting the voice recognition process. At this time, the voice recognition processing may be started from the start of pressing the hardware button to the release of pressing (Push To Talk type). Alternatively, the activation trigger for the voice recognition process may be an execution of a voice recognition process activation command (for example, an utterance “voice”).

  Alternatively, the voice recognition process activation trigger is a predetermined voice recognition process activation gesture (for example, raising a hand, swinging a hand down, moving a face (for example, nodding, tilting the face to the left or right, etc.)). May be. In addition, the activation trigger of the voice recognition process may include that sound information whose voice likelihood exceeds a threshold is acquired from the sound collection unit 120.

  First, an example in which the remaining time until the voice recognition process is started is output as the start condition will be described.

  FIG. 5 is a diagram illustrating an example of screen transition from when the remaining time until the voice recognition process is started as a start condition until the voice recognition process is started. When the activation trigger for the speech recognition process is detected, the output control unit 146 starts outputting the remaining time notification screen G21-1 (time T11). The remaining time notification screen G21-1 includes a remaining time G23-1 until the voice recognition process is started and a cancellation object G22 for stopping the output of the start condition.

  Subsequently, the output control unit 146 decreases the remaining time G23-1 as time elapses. For example, the output control unit 146 causes the remaining time notification screen G21-2 including the remaining time G23-2 after being reduced from the remaining time G23-1 to be output. Subsequently, when the remaining time until the voice recognition process is started becomes zero and the start condition is satisfied (time T12), the output control unit 146 stops outputting the start condition (time T13). When the output of the start condition is stopped, the user starts speaking toward the sound collection unit 120 (time T14).

  When the sound information collected by the sound collection unit 120 is acquired by the sound information acquisition unit 142, the output control unit 146 displays a predetermined object (hereinafter also referred to as “display object”) Mu. The display object Mu may be stationary or may have a movement. For example, when the display object Mu has a movement, the moving direction De of the display object Mu may be determined according to the arrival direction from the sound source of the uttered voice by the user to the sound collection unit 120. In addition, the estimation method of the arrival direction of the uttered voice by the user is not particularly limited.

  For example, the recognition control unit 144 utters one arrival direction that matches or is similar to the finger direction of the user who performed the operation of selecting the voice recognition start operation object G14 (for example, the direction from the base of the finger to the fingertip). It may be estimated as the voice arrival direction. The similarity range may be determined in advance. The finger direction may be obtained by analyzing the input image.

  Alternatively, the recognition control unit 144 may estimate the arrival direction of the sound input by the sound collection unit 120 as the arrival direction of the uttered speech by the user. When there are a plurality of sound arrival directions, the arrival direction of the sound input first among the plurality of arrival directions may be estimated as the arrival direction of the uttered voice by the user. One arrival direction that matches or resembles the direction of the finger of the user who has performed the operation of selecting the recognition start operation object G14 may be estimated as the arrival direction of the uttered voice by the user.

  Or the recognition control part 144 may estimate the arrival direction of the sound input with the loudest volume by the sound collection part 120 among several arrival directions as an arrival direction of the speech sound by a user. In this way, the arrival direction of the uttered voice by the user can be estimated. On the other hand, the recognition control unit 144 may acquire the sound input by the sound collection unit 120 from a direction other than the arrival direction of the uttered voice by the user as noise. Therefore, the noise may include an output sound from the information processing system 10.

  FIG. 5 shows an example in which the output control unit 146 moves the display object Mu in the direction of arrival of the uttered voice by the user (movement direction De). As a result, the user can intuitively understand that his / her speech is being collected by the sound collection unit 120. However, the movement of the display object Mu is not limited to such movement. FIG. 5 shows an example in which the movement destination of the display object Mu is the voice recognition start operation object G14. However, the movement destination of the display object Mu is not limited to this example.

  FIG. 5 shows an example in which the output control unit 146 moves the circular display objects Mu that appear one after another according to the sound collection by the sound collection unit 120. However, the display mode of the display object Mu is shown. Is not limited to such an example. For example, the output control unit 146 may control various parameters of the display object Mu based on predetermined information corresponding to the sound information (for example, sound quality, sound volume, etc. of the sound information). The sound information used at this time may be sound information from the direction of arrival of the uttered voice by the user. The parameter of the display object Mu may include at least one of the shape, transparency, color, size, and movement of the display object Mu.

  Note that there is no particular limitation on the method for evaluating the sound quality from the sound information. For example, a technique described in a patent document (Japanese Patent Laid-Open No. 2010-38943) can be employed as a technique for evaluating the likelihood of sound from sound information. In addition, for example, as a method for evaluating the likelihood of sound from sound information, a method described in a patent document (Japanese Patent Laid-Open No. 2007-328228) can be employed. Here, an example is described in which the speech likelihood evaluation is performed by the output control unit 146, but the speech likelihood evaluation may be performed by a server (not shown).

  When the start condition is satisfied, the recognition control unit 144 causes the voice recognition unit 145 to start voice recognition processing for the sound information acquired by the sound information acquisition unit 142. The timing for starting the speech recognition process is not limited. For example, the recognition control unit 144 may cause the speech recognition unit 145 to start after the sound information whose soundness exceeds the predetermined threshold is collected, or the display object Mu reaches the speech recognition start operation object G14. Then, the speech recognition unit 145 may start speech recognition processing for sound information corresponding to the display object Mu.

  Note that when the user wants to cancel the start of the speech recognition process, the cancel object G22 may be selected. When the user selects the cancel object G22, this operation is input by the operation input unit 115 as an output stop operation, and the output stop operation is detected by the operation detection unit 143. When the output detection operation is detected by the operation detection unit 143, the output control unit 146 stops the output of the start condition.

  Heretofore, the example in which the remaining time until the voice recognition process is started is output as the start condition has been described. Next, an example will be described in which information related to a user operation necessary for starting the speech recognition process is output as a start condition.

  FIG. 6 is a diagram illustrating an example of screen transition from when information related to a user operation necessary for starting the voice recognition process is output as a start condition until the voice recognition process is started. When the activation trigger for the speech recognition process is detected, the output control unit 146 starts outputting the utterance start confirmation screen G24-1 (time T11). The utterance start confirmation screen G24-1 includes a speech recognition process start object G25-1 and a cancellation object G22 as information related to user operations necessary for starting the speech recognition process.

  Subsequently, when the user performs an operation of selecting the speech recognition processing start object G25-1 (speech start confirmation screen G24-2), the operation is input by the operation input unit 115 and detected by the operation detection unit 143. . When the operation for selecting the speech recognition process start object G25-1 is detected and the start condition is satisfied (time T12), the output control unit 146 stops outputting the start condition (time T13). When the output of the start condition is stopped, the user starts speaking toward the sound collection unit 120 (time T14). Subsequent operations can be executed in the same manner as in the example in which the remaining time until the voice recognition process already described is started is output as the start condition.

  Heretofore, an example has been described in which information regarding user operations necessary to start the speech recognition process is output as the start condition. By outputting the start condition of the voice recognition process, the user collects sound information (for example, filler and extra utterances) collected before the start of utterance as shown in FIG. 5 and FIG. It is possible to reduce the influence on the recognition process.

  Although the start condition can be output in this way, if the start condition is unchanged, it is difficult to start the voice recognition process flexibly according to the situation. Therefore, in the embodiment of the present disclosure, the output control unit 146 dynamically changes the start condition of the voice recognition process to be output to the output unit 130. With this configuration, the voice recognition process can be started flexibly according to the situation. For example, the output control unit 146 may dynamically change the start condition of the voice recognition process to be output to the output unit 130 based on predetermined information.

  The predetermined information is not particularly limited. First, an example will be described in which the start condition to be output to the output unit 130 is dynamically changed based on sound information input from the sound collection unit 120 after the activation trigger of the speech recognition process is detected. FIG. 7 is a diagram for explaining an example in which the start condition is dynamically changed based on the sound information input from the sound collection unit 120 after the activation trigger for the speech recognition process is detected.

  As shown in FIG. 7, when an operation for selecting the voice recognition start operation object G14 by the user is input by the operation input unit 15, the operation is detected by the operation detection unit 143 as a trigger for starting the voice recognition process (time). T10). When the activation trigger of the speech recognition process is detected, the output control unit 146 causes the output unit 130 to output based on the first type of sound information included in the sound information input from the sound collection unit 120. To change dynamically.

  Here, the first type of sound information is not particularly limited. For example, the first type of sound information may include at least noise. This is because the noise may interfere with the voice recognition process for the user's utterance. Here, the description will be continued by taking as an example the case where the first type of sound information is noise.

  First, when the volume of noise (hereinafter, also referred to as “noise level”) exceeds the first threshold value n1, the success rate of the speech recognition processing for the user's utterance is low. It may be desirable to input the start timing of the recognition process. Therefore, when the noise level exceeds the first threshold value n1, the output control unit 146 may change the start condition to information related to user operation necessary to start the voice recognition process.

  More specifically, the output control unit 146 may output the utterance start confirmation screen G24-1 when the noise level exceeds the first threshold value n1. Similar to the above-described example, the speech start confirmation screen G24-1 includes a speech recognition processing start object G25-1 and a cancellation object G22 as information related to user operations necessary for starting the speech recognition processing. Yes.

  Subsequently, when the user performs an operation of selecting the speech recognition processing start object G25-1, the operation is input by the operation input unit 115 and detected by the operation detection unit 143. When the operation for selecting the speech recognition process start object G25-1 is detected and the start condition is satisfied (time T12), the output control unit 146 stops outputting the start condition (time T13). The subsequent operation is as described above.

  Second, when the noise level is equal to or lower than the first threshold value n1 and the noise level is equal to or higher than the second threshold value n2 (which is smaller than the first threshold value n1), speech recognition for the user's utterance is performed. Since the success rate of the process is moderate, it is desirable to automatically start the speech recognition process after a predetermined time has elapsed. Therefore, the output control unit 146 starts at the remaining time until the voice recognition process is started when the volume of the noise is lower than the first threshold value n1 and when the noise level is higher than the second threshold value n2. It is better to change the conditions.

  Similar to the above-described example, the remaining time notification screen G21-1 includes a remaining time G23-1 until the voice recognition process is started and a cancellation object G22 for stopping the output of the start condition. . When the remaining time until the voice recognition process is started becomes zero and the start condition is satisfied (time T12), the output control unit 146 stops outputting the start condition (time T13). The start condition output is stopped. The subsequent operation is as described above.

  Third, when the noise level is lower than the second threshold value n2, the success rate of the speech recognition process for the user's utterance is high, so the speech recognition process is started without outputting the start condition. Is desirable. Therefore, it is desirable that the output control unit 146 omits outputting the start condition to the output unit 130 when the noise level falls below the second threshold value n2.

  In the above, when the noise level is equal to the first threshold value n1, it is handled in the same manner as when the noise level is equal to or lower than the first threshold value n1 and when the noise level is equal to or higher than the second threshold value n2. However, it may be handled in the same manner as when the noise level exceeds the first threshold value n1. Further, in the above, when the noise level is equal to the second threshold value n2, it is handled in the same manner as when the noise level is equal to or lower than the first threshold value n1 and the noise level is equal to or higher than the second threshold value n2. However, it may be handled in the same manner as when the noise level is lower than the second threshold value n2.

  The output control unit 146 may cause the output unit 130 to output predetermined display information as a start condition. 8 and 9 are diagrams illustrating an example in which display information is output to the output unit 130 as a start condition. FIG. 8 shows an example in which the display content gradually appears on the voice recognition start operation object G14 (time T31 to time T36). FIG. 9 shows an example in which the color of the voice recognition start operation object G14 is gradually changed (time T41 to time T46).

  Further, the output control unit 146 may cause the output unit 130 to output predetermined audio information as a start condition. 10 and 11 are diagrams illustrating an example in which audio information is output to the output unit 130 as a start condition. FIG. 10 shows an example in which voice information that informs the start timing (time T54) of the voice recognition process is output from time T51 to time T54. Further, FIG. 11 shows an example in which voice information that informs the start timing (time T64) of voice recognition processing is output from time T61 to time T64.

  Subsequently, referring to FIG. 12 and FIG. 13, the start condition to be output to the output unit 130 is dynamically set based on the sound information input from the sound collection unit 120 after the activation trigger of the speech recognition process is detected. The operation flow to be changed will be described. The flowcharts of FIGS. 12 and 13 dynamically change the start condition to be output to the output unit 130 based on the sound information input from the sound collection unit 120 after the activation trigger of the speech recognition process is detected. Since this is merely an example of the flow of operation, the flow of such operation is not limited to the examples shown in the flowcharts of FIGS.

  First, as shown in FIG. 12, the operation detection unit 143 detects the activation trigger of the voice recognition process (S11), and the sound information v1 is input from the sound collection unit 120 (S12). Subsequently, the output control unit 146 dynamically determines the start condition of the speech recognition process based on the noise (S13). Here, the details of the operation for dynamically determining the start condition of the speech recognition process based on noise will be described with reference to FIG. First, the output control unit 146 acquires the sound information v1 (S131), and when the noise level of the sound information v1 exceeds the threshold value n1 (“Yes” in S132), the modal UI (in the above example, the utterance start) It is determined to output the confirmation screen G24-1) (S133).

  On the other hand, if the noise level of the sound information v1 does not exceed the threshold value n1 (“No” in S132), the output control unit 146 proceeds to S134, and if the noise level of the sound information v1 is lower than the threshold value n2 (in S134) "Yes"), it is determined not to output the start condition (S135), and if the noise level of the sound information v1 does not fall below the threshold value n2 ("No" in S134), the timer UI (remaining time notification screen G21- 1) is determined to be output (S136).

  Returning to FIG. 12, the description will be continued. When the output control unit 146 determines to omit the output of the start condition (“Yes” in S14), the output control unit 146 shifts the operation to S18. On the other hand, when it is determined that the output of the start condition is not omitted (“No” in S14), the output control unit 146 outputs the start condition (S15). Thereafter, the operation detection unit 143 detects an output stop trigger of the start condition (S16). The output stop trigger of the start condition may include an operation of selecting the cancel object G22 for stopping the output of the start condition and the start condition being satisfied.

  Subsequently, the output control unit 146 stops outputting the start condition. Then, when the start condition is not satisfied (“No” in S17), the voice recognition unit 145 ends the operation without starting the voice recognition process (S19). On the other hand, when the start condition is satisfied (“Yes” in S17), the voice recognition unit 145 starts the voice recognition process (S18).

  In the above, the example in which the start condition to be output to the output unit 130 is dynamically changed based on the sound information input from the sound collection unit 120 after the activation trigger of the speech recognition process is detected has been described.

  Subsequently, the start condition to be output to the output unit 130 is dynamically changed based on the past sound information collected in a predetermined time after the activation trigger is detected in the past until the voice recognition process is started. An example will be described. FIGS. 14 and 15 show the time until the voice recognition process is started based on the past sound information collected at a predetermined time after the activation trigger is detected in the past until the voice recognition process is started. It is a figure for demonstrating the example which shortens remaining time dynamically.

  As shown in the upper part of FIG. 14, when an operation for selecting the speech recognition start operation object G14 by the user is input by the operation input unit 15 in the first speech recognition process, the operation is used as a start trigger for the speech recognition process. It is detected by the operation detection unit 143 (time T10). When the activation trigger for the speech recognition processing is detected, the output control unit 146 starts accumulating sound information input from the sound collection unit 120 and starts outputting the remaining time notification screen G21-1 (time T11). . As described above, the remaining time notification screen G21-1 includes the remaining time G23-1 until the voice recognition process is started and the cancellation object G22 for stopping the output of the start condition.

  Subsequently, the output control unit 146 decreases the remaining time G23-1 as time elapses. For example, the output control unit 146 causes the remaining time notification screen G21-2 including the remaining time G23-2 after being reduced from the remaining time G23-1 to be output. Subsequently, when the remaining time until the voice recognition process is started becomes zero and the start condition is satisfied (time T12), the output control unit 146 stops outputting the start condition (time T13).

  When the output of the start condition is stopped, the output control unit 146 ends the accumulation of the sound information input from the sound collection unit 120. The sound information accumulated in this way is used as the past sound information in the next speech recognition process. Then, the user starts speaking toward the sound collection unit 120 (time T14). Subsequent operations can be executed in the same manner as in the example in which the remaining time until the voice recognition process already described is started is output as the start condition.

  Subsequently, as shown in the lower part of FIG. 14, when an operation for selecting the speech recognition start operation object G14 by the user is input by the operation input unit 15 in the second speech processing, the operation is performed in the speech recognition processing. It is detected by the operation detection unit 143 as an activation trigger (time T10). When the activation trigger for the voice recognition process is detected, the output control unit 146 acquires the accumulated past sound information, starts accumulating the sound information input from the sound collecting unit 120, and displays the remaining time notification screen The output of G21-1 is started (time T11).

  At this time, the output control unit 146 dynamically changes the start condition to be output to the output unit 130 based on the second type of sound information included in the past sound information. Here, the second type of sound information is not particularly limited. For example, the second type of sound information may include at least noise. This is because the noise may interfere with the voice recognition process for the user's utterance. Here, the description will be continued by taking as an example the case where the second type of sound information is noise.

  Here, as shown in the upper part of FIG. 14, at the time of the first speech recognition processing, the noise level was lower than the threshold until the start condition output was stopped after the start trigger of the speech recognition processing was detected. Assume a case. In such a case, the noise level at the time of the first voice recognition process acquired at the time of the second voice recognition process is smaller than the threshold value. In such a case, the output control unit 146 shortens the remaining time until the voice recognition process to be output as the start condition is started compared to the time of the first voice recognition process.

  More specifically, referring to FIG. 14, the output control unit 146 sets the remaining time G23-1 until the voice recognition process is started as “3” seconds in the first voice recognition process. On the other hand, in the second speech recognition process, the time is shortened to “1” seconds. In the example shown in FIG. 14, the remaining time G23-1 until the voice recognition process is started is immediately shortened during the second voice recognition process, but the state where the noise level is smaller than the threshold value continues several times. For the first time, the remaining time G23-1 until the voice recognition process is started may be shortened.

  Next, as shown in FIG. 15, when an operation for selecting the speech recognition start operation object G14 by the user is input by the operation input unit 15 in the third speech recognition process, the operation is activated by the speech recognition process. It is detected as a trigger by the operation detection unit 143 (time T10). When the activation trigger for the speech recognition process is detected, the output control unit 146 starts accumulating the sound information input from the sound collection unit 120 during the accumulated second speech recognition process (time T11).

  Here, as shown in the lower part of FIG. 14, in the second speech recognition process, the noise level is lower than the threshold until the start condition output is stopped after the start trigger of the speech recognition process is detected. Assuming that In such a case, the noise level at the time of the second day speech recognition processing acquired at the time of the third speech recognition processing is smaller than the threshold value. In such a case, the output control unit 146 shortens the remaining time until the voice recognition process to be output as the start condition is started compared to the time of the voice recognition process on the second day.

  More specifically, referring to FIG. 15, the output control unit 146 sets the remaining time G23-1 until the voice recognition process is started as “1” seconds at the time of the voice recognition process on the second day. On the other hand, during the third speech recognition process, the output of the remaining time notification screen G21-1 is omitted. In the example shown in FIG. 15, the output of the remaining time notification screen G21-1 is immediately omitted at the time of the third speech recognition process, but the remaining time is not reached until the state where the noise level is lower than the threshold value continues several times. The output of the notification screen G21-1 may be omitted.

  Next, an example in which the remaining time until the voice recognition process is started is dynamically increased will be described. 16 and FIG. 17 show the time until the voice recognition process is started based on the past sound information collected at a predetermined time after the activation trigger is detected in the past until the voice recognition process is started. It is a figure for demonstrating the example which lengthens remaining time dynamically.

  As shown in the upper part of FIG. 16, when an operation for selecting the speech recognition start operation object G14 by the user is input by the operation input unit 15 in the first speech recognition process, the operation is used as a start trigger for the speech recognition process. It is detected by the operation detection unit 143 (time T10). When the activation trigger for the speech recognition processing is detected, the output control unit 146 starts accumulating sound information input from the sound collection unit 120 and starts outputting the remaining time notification screen G21-1 (time T11). . Subsequent operations can be executed in the same manner as in the example in which the remaining time until the voice recognition process already described is started is output as the start condition.

  Subsequently, as shown in the lower part of FIG. 16, when an operation for selecting the speech recognition start operation object G14 by the user is input by the operation input unit 15 in the second speech processing, the operation is performed in the speech recognition processing. It is detected by the operation detection unit 143 as an activation trigger (time T10). When the activation trigger for the voice recognition process is detected, the output control unit 146 acquires the accumulated past sound information, starts accumulating the sound information input from the sound collecting unit 120, and displays the remaining time notification screen The output of G21-1 is started (time T11).

  Here, as shown in the upper part of FIG. 16, at the time of the first speech recognition processing, the noise level was larger than the threshold until the start condition output was stopped after the start trigger of the speech recognition processing was detected. Assume a case. In such a case, the noise level at the time of the first voice recognition process acquired at the time of the second voice recognition process is larger than the threshold value. In such a case, the output control unit 146 makes the remaining time until the voice recognition process to be output as the start condition is started longer than that in the first voice recognition process.

  More specifically, referring to FIG. 16, the output control unit 146 sets the remaining time G23-1 until the voice recognition process is started as “3” seconds in the first voice recognition process. On the other hand, in the second speech recognition process, it is set to “5” seconds. In the example shown in FIG. 16, the remaining time G23-1 until the voice recognition process is started is immediately longer during the second voice recognition process, but the state where the noise level is larger than the threshold value continues several times. For the first time, the remaining time G23-1 until the voice recognition process is started may be longer.

  Subsequently, as shown in FIG. 17, when an operation for selecting the speech recognition start operation object G14 by the user is input by the operation input unit 15 in the third speech recognition process, the operation starts the speech recognition process. It is detected as a trigger by the operation detection unit 143 (time T10). When the activation trigger for the speech recognition process is detected, the output control unit 146 starts accumulating the sound information input from the sound collection unit 120 during the accumulated second speech recognition process (time T11).

  Here, as shown in the lower part of FIG. 16, in the second speech recognition process, the noise level is higher than the threshold until the start condition output is stopped after the start trigger of the speech recognition process is detected. Assuming that In such a case, the noise level at the time of the voice recognition process on the second day acquired at the time of the third voice recognition process is larger than the threshold value. In such a case, the output control unit 146 makes the remaining time until the voice recognition process to be output as the start condition is started longer than that during the voice recognition process on the second day.

  More specifically, referring to FIG. 17, the output control unit 146 sets the remaining time G23-1 until the voice recognition process is started as “5” seconds at the time of the voice recognition process on the second day. On the other hand, during the third speech recognition process, the utterance start confirmation screen G24-2 is output. In the example shown in FIG. 17, the utterance start confirmation screen G24-2 is immediately output at the time of the third speech recognition process. However, the utterance start confirmation screen is not displayed until the state where the noise level is greater than the threshold value continues several times. G24-2 may be output.

  Here, as described above, the remaining time until the voice recognition process is started may change. At this time, it is preferable to change the display information output to the output unit 130 as the remaining time until the voice recognition process is started. Then, it becomes possible for the user to easily grasp that the start condition has been changed.

  FIG. 18 is a diagram illustrating an example of display information when the remaining time until the voice recognition process is started is shortened. As shown in FIG. 18, in the example in which the display content gradually appears on the speech recognition start operation object G14, the output control unit 146 may increase the appearance speed of the display content (time T31 to time T33). . FIG. 19 is a diagram illustrating an example of display information when the remaining time until the voice recognition process is started is long. As shown in FIG. 19, in the example in which the display content gradually appears on the speech recognition start operation object G14, the output control unit 146 may reduce the appearance speed of the display content (time T31 to time T38). .

  Next, referring to FIGS. 20 and 21, the output unit 130 is based on past sound information collected in a predetermined time after the activation trigger is detected in the past until the voice recognition process is started. The flow of the operation for dynamically changing the start condition to be output to will be described. Note that the flowcharts of FIGS. 20 and 21 are output to the output unit 130 based on past sound information collected in a predetermined time after the activation trigger is detected in the past until the voice recognition process is started. Since this is merely an example of an operation flow for dynamically changing the starting condition to be performed, the operation flow is not limited to the examples shown in the flowcharts of FIGS. 20 and 21.

  First, as illustrated in FIG. 20, the operation detection unit 143 detects a start trigger for voice recognition processing (S <b> 21). Further, if there is past sound information h1, the output control unit 146 acquires the past sound information h1 (S22), and starts acquiring the sound information v1 from the sound collection unit 120 (S23). Subsequently, the output control unit 146 dynamically determines the start condition of the voice recognition process according to the past sound information h1 (S24). Here, the details of the operation for dynamically determining the start condition of the speech recognition process based on the past sound information h1 will be described with reference to FIG.

  First, the output control unit 146 acquires past sound information h1 (S241), and acquires a timeout value t1 (in the above example, the remaining time G23-1 until the voice recognition process is started) (S242). . Subsequently, when the volume of the past sound information h1 exceeds the threshold value m1 (“Yes” in S243), the output control unit 146 shifts the operation to S244. On the other hand, when the volume of the past sound information h1 does not exceed the threshold value m1 (“No” in S243), the output control unit 146 shifts the operation to S248.

  When the operation is shifted to S244, the output control unit 146, when the timeout value t1 exceeds the threshold value t_max (“Yes” in S244), the modal UI (in the above example, the utterance start confirmation screen G24− 1) is output (S245), and if the timeout value t1 does not exceed the threshold value t_max (“No” in S244), the timeout value t1 is increased (S246), and the timeout value t1 is set. The timer UI (in the above, the remaining time notification screen G21-1) is determined to be output (S247).

  On the other hand, when the operation is shifted to S248, the output control unit 146 determines not to output the start condition when the timeout value t1 is lower than the threshold value t_min (“Yes” in S248) (S251). If the timeout value t1 is not lower than the threshold value t_min (“No” in S248), the timeout value t1 is decreased (S249), and the timer UI in which the timeout value t1 is set (in the above, remaining time notification screen G21) -1) is determined to be output (S247).

  Returning to FIG. 20, the description will be continued. If the output control unit 146 determines that the output of the start condition is omitted (“Yes” in S25), the output control unit 146 shifts the operation to S30. On the other hand, when it is determined that the output of the start condition is not omitted (“No” in S25), the output control unit 146 outputs the start condition (S26). Thereafter, the operation detection unit 143 detects an output stop trigger of the start condition (S27). The output stop trigger of the start condition may include an operation of selecting the cancel object G22 for stopping the output of the start condition and the start condition being satisfied.

  Subsequently, the output control unit 146 stops outputting the start condition, and stores the continuously acquired sound information v1 as past sound information h1 (S28). Then, when the start condition is not satisfied (“No” in S29), the voice recognition unit 145 ends the operation without starting the voice recognition process (S31). On the other hand, when the start condition is satisfied (“Yes” in S29), the voice recognition unit 145 starts the voice recognition process (S30).

  As described above, the start condition to be output to the output unit 130 is dynamically changed based on the past sound information collected in a predetermined time after the activation trigger is detected in the past until the voice recognition process is started. An example was explained.

  In the above, an example has been described in which the sound information input from the sound collection unit 120 operates regardless of whether or not a filler is included, but the sound information input from the sound collection unit 120 includes a filler. The operation may be different depending on whether or not it is. First, an example of the filler will be described. FIG. 22 is a diagram illustrating an example of a correspondence relationship between a filler and its speech waveform. As shown in FIG. 22, information in which fillers and their speech waveforms are associated with each other is stored in advance. When this voice waveform is included in the sound information input from the sound collection unit 120, a filler corresponding to this voice waveform is acquired as a result of the voice recognition process.

  FIG. 23 is a diagram for explaining an example in which the operation is varied depending on whether or not the sound information input from the sound collection unit 120 includes a filler. When the activation trigger for the speech recognition process is detected, the output control unit 146 starts outputting the remaining time notification screen G21-1 (time T11). At this time, the recognition control unit 144 starts accumulating sound information input from the sound collection unit 120.

  Subsequently, when the start condition is satisfied (time T12), the recognition control unit 144 determines whether the recognition result of the sound information P1 accumulated until the start condition is satisfied is a filler. In the case of the filler, the speech recognition unit 145 performs speech recognition processing by excluding P1 accumulated until the start condition is satisfied from the sound information P2 accumulated up to the present time. On the other hand, when the recognition result is not a filler, the recognition control unit 144 performs the voice recognition processing without excluding P1 accumulated until the start condition is satisfied from the sound information P2 accumulated up to the present time. To do. Further, when the start condition is satisfied (time T12), the output control unit 146 stops outputting the start condition (time T13). The subsequent operation is as described above.

  The example in which the start condition to be output to the output unit 130 is dynamically changed has been described above, but the example in which the start condition is dynamically changed is not limited to the above example. For example, the output control unit 146 may dynamically change the start condition to be output to the output unit 130 based on the number of arrival directions of sound information whose sound quality exceeds a threshold value to the sound collection unit 120. This is because if the number of arrival directions of sound information whose sound quality exceeds the threshold exceeds the predetermined value, the speech recognition process may be difficult.

  Therefore, for example, the output control unit 146 may output the utterance start confirmation screen G24-1 when the number of arrival directions of sound information whose sound quality exceeds the threshold exceeds the predetermined value. Good. Further, the output control unit 146 may cause the remaining time notification screen G21-1 to be output when the number of arrival directions of the sound information whose sound quality exceeds the threshold value to the sound collection unit 120 is equal to or less than a predetermined value. . The predetermined value is not limited, but may be “1”.

  The function details of the information processing system 10 according to the embodiment of the present disclosure have been described above.

[1.4. Modification of system configuration]
In the above, the example in which the output unit 130 is a projector capable of projecting a screen onto the top surface of the table Tbl has been described. However, the system configuration of the information processing system 10 is not limited to this example. Below, the modification of the system configuration | structure of the information processing system 10 is demonstrated. FIG. 24 is a diagram illustrating a first modification of the configuration of the information processing system 10. As illustrated in FIG. 24, when the information processing system 10 is a mobile terminal, the output unit 130 may be included in the mobile terminal. The kind of portable terminal is not specifically limited, A tablet terminal may be sufficient, a smart phone may be sufficient, and a mobile phone may be sufficient.

  25 to 28 are diagrams illustrating a second modification of the configuration of the information processing system 10. As illustrated in FIGS. 25 to 28, the output unit 130 may be a television device, the information processing device 140 may be a game machine, and the operation input unit 115 may be a controller that operates the game machine.

  Further, as shown in FIG. 25, the sound collection unit 120 and the output unit 130 may be connected to the operation input unit 115. In addition, as illustrated in FIG. 26, the image input unit 110 and the sound collection unit 120 may be connected to the information processing apparatus 140. As illustrated in FIG. 27, the operation input unit 115, the sound collection unit 120, and the output unit 130 may be provided in a smartphone connected to the information processing apparatus 140. As shown in FIG. 28, the sound collection unit 120 may be provided in a television device.

  FIGS. 29 to 32 are diagrams showing a third modification of the configuration of the information processing system 10. As shown in FIG. 29, the information processing system 10 may be mounted on a vehicle-mounted navigation system that can be attached to a vehicle and used by a user U who is driving the vehicle. As shown in FIG. 30, the information processing system 10 may be mounted on a mobile terminal and used by a user U who is driving a car. As described above, the type of mobile terminal is not particularly limited.

  As shown in FIG. 31, in the information processing system 10, the image input unit 110, the operation input unit 115, and the output unit 130 are provided by a mobile terminal, and the sound collection unit 120 It may be a microphone that can be attached to the body. As shown in FIG. 32, the information processing system 10 may be mounted on an in-vehicle navigation system built in an automobile and used by a user U driving the automobile.

[1.5. Hardware configuration example]
Next, a hardware configuration of the information processing system 10 according to the embodiment of the present disclosure will be described with reference to FIG. FIG. 33 is a block diagram illustrating a hardware configuration example of the information processing system 10 according to the embodiment of the present disclosure.

  As illustrated in FIG. 33, the information processing system 10 includes a central processing unit (CPU) 901, a read only memory (ROM) 903, and a random access memory (RAM) 905. The information processing system 10 may also include a host bus 907, a bridge 909, an external bus 911, an interface 913, an input device 915, an output device 917, a storage device 919, a drive 921, a connection port 923, and a communication device 925. Furthermore, the information processing system 10 may include an imaging device 933 and a sensor 935 as necessary. The information processing system 10 may include a processing circuit called DSP (Digital Signal Processor) or ASIC (Application Specific Integrated Circuit) instead of or in addition to the CPU 901.

  The CPU 901 functions as an arithmetic processing device and a control device, and controls all or a part of the operation in the information processing system 10 according to various programs recorded in the ROM 903, the RAM 905, the storage device 919, or the removable recording medium 927. The ROM 903 stores programs and calculation parameters used by the CPU 901. The RAM 905 temporarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution, and the like. The CPU 901, the ROM 903, and the RAM 905 are connected to each other by a host bus 907 configured by an internal bus such as a CPU bus. Further, the host bus 907 is connected to an external bus 911 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 909.

  The input device 915 is a device operated by the user, such as a mouse, a keyboard, a touch panel, a button, a switch, and a lever. The input device 915 may include a microphone that detects the user's voice. The input device 915 may be, for example, a remote control device using infrared rays or other radio waves, or may be an external connection device 929 such as a mobile phone that supports the operation of the information processing system 10. The input device 915 includes an input control circuit that generates an input signal based on information input by the user and outputs the input signal to the CPU 901. The user operates the input device 915 to input various data to the information processing system 10 and instruct processing operations. An imaging device 933, which will be described later, can also function as an input device by imaging a user's hand movement, a user's finger, and the like. At this time, the pointing position may be determined according to the movement of the hand or the direction of the finger.

  The output device 917 is configured by a device capable of visually or audibly notifying acquired information to the user. The output device 917 is, for example, an LCD (Liquid Crystal Display), a PDP (Plasma Display Panel), an organic EL (Electro-Luminescence) display, a display device such as a projector, a hologram output device, an audio output device such as a speaker and headphones, As well as a printer device. The output device 917 outputs the result obtained by the processing of the information processing system 10 as a video such as text or an image, or outputs it as a voice such as voice or sound. The output device 917 may include a light or the like to brighten the surroundings.

  The storage device 919 is a data storage device configured as an example of a storage unit of the information processing system 10. The storage device 919 includes, for example, a magnetic storage device such as an HDD (Hard Disk Drive), a semiconductor storage device, an optical storage device, or a magneto-optical storage device. The storage device 919 stores programs executed by the CPU 901, various data, various data acquired from the outside, and the like.

  The drive 921 is a reader / writer for a removable recording medium 927 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and is built in or externally attached to the information processing system 10. The drive 921 reads information recorded on the attached removable recording medium 927 and outputs the information to the RAM 905. In addition, the drive 921 writes a record in the attached removable recording medium 927.

  The connection port 923 is a port for directly connecting a device to the information processing system 10. The connection port 923 may be, for example, a USB (Universal Serial Bus) port, an IEEE 1394 port, a SCSI (Small Computer System Interface) port, or the like. The connection port 923 may be an RS-232C port, an optical audio terminal, an HDMI (registered trademark) (High-Definition Multimedia Interface) port, or the like. Various data can be exchanged between the information processing system 10 and the external connection device 929 by connecting the external connection device 929 to the connection port 923.

  The communication device 925 is a communication interface configured with, for example, a communication device for connecting to the communication network 931. The communication device 925 can be, for example, a communication card for wired or wireless LAN (Local Area Network), Bluetooth (registered trademark), or WUSB (Wireless USB). The communication device 925 may be a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various communication. The communication device 925 transmits and receives signals and the like using a predetermined protocol such as TCP / IP with the Internet and other communication devices, for example. The communication network 931 connected to the communication device 925 is a wired or wireless network, such as the Internet, a home LAN, infrared communication, radio wave communication, or satellite communication.

  The imaging device 933 uses various members such as an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor), and a lens for controlling the formation of a subject image on the imaging element. It is an apparatus that images a real space and generates a captured image. The imaging device 933 may capture a still image or may capture a moving image.

  The sensor 935 is various sensors such as an acceleration sensor, a gyro sensor, a geomagnetic sensor, an optical sensor, and a sound sensor. The sensor 935 obtains information related to the state of the information processing system 10 such as the posture of the information processing system 10, and information related to the surrounding environment of the information processing system 10 such as brightness and noise around the information processing system 10. To do. The sensor 935 may also include a GPS sensor that receives a GPS (Global Positioning System) signal and measures the latitude, longitude, and altitude of the device.

  Heretofore, an example of the hardware configuration of the information processing system 10 has been shown. Each component described above may be configured using a general-purpose member, or may be configured by hardware specialized for the function of each component. Such a configuration can be appropriately changed according to the technical level at the time of implementation.

<2. Conclusion>
As described above, according to the embodiment of the present disclosure, the output that causes the output unit 130 to output the start condition of the voice recognition process performed by the voice recognition unit 145 on the sound information input from the sound collection unit 120. The information processing system 10 is provided that includes a control unit 146, and the output control unit 146 dynamically changes the start condition of the speech recognition processing to be output to the output unit 130. According to such a configuration, it is possible to flexibly start the voice recognition process according to the situation.

  Moreover, according to this structure, it becomes possible to make a user think the utterance content before the voice recognition process is started. In other words, the speech recognition process can be started after the user determines the utterance content. Further, according to such a configuration, it is possible to exclude noise included in the collected sound information from the target of speech recognition processing. In addition, the success rate of the speech recognition process can be improved by presenting the user with the start conditions of the speech recognition process.

  The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, but the technical scope of the present disclosure is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field of the present disclosure can come up with various changes or modifications within the scope of the technical idea described in the claims. Of course, it is understood that it belongs to the technical scope of the present disclosure.

  For example, in the above description, the system configuration example of the information processing system 10 and the modification examples of the system configuration have been described. However, the system configuration example of the information processing system 10 is not limited to these examples. For example, the output unit 130 may be a display provided in a wearable terminal (for example, a watch, glasses, etc.) other than the head mounted display. For example, the output unit 130 may be a display used in the healthcare field.

  In addition, it is possible to create a program for causing hardware such as a CPU, ROM, and RAM incorporated in a computer to exhibit functions equivalent to the functions of the information processing apparatus 140 described above. Also, a computer-readable recording medium that records the program can be provided.

  Further, the output control unit 146 generates display control information for causing the output unit 130 to display the display content, and outputs the generated display control information to the output unit 130, so that the display content is displayed on the output unit 130. The output unit 130 can be controlled as described above. The contents of the display control information may be changed as appropriate according to the system configuration.

  As a specific example, the program for realizing the information processing apparatus 140 may be a web application. In such a case, the display control information may be realized by a markup language such as HTML (HyperText Markup Language), SGML (Standard Generalized Markup Language), or XML (Extensible Markup Language).

  Note that the position of each component is not particularly limited as long as the operation of the information processing system 10 described above is realized. As a specific example, the image input unit 110, the operation input unit 115, the sound collecting unit 120, the output unit 130, and the information processing device 140 may be provided in different devices connected via a network. In this case, the information processing apparatus 140 corresponds to a server such as a web server or a cloud server, and the image input unit 110, the operation input unit 115, the sound collection unit 120, and the output unit 130 are connected to the server. It may correspond to a client connected via

  In addition, all the components included in the information processing apparatus 140 may not be accommodated in the same apparatus. For example, among the input image acquisition unit 141, the sound information acquisition unit 142, the operation detection unit 143, the recognition control unit 144, the voice recognition unit 145, and the output control unit 146, some of them are the information processing device 140. May be present on different devices. For example, the voice recognition unit 145 is a server different from the information processing apparatus 140 including the input image acquisition unit 141, the sound information acquisition unit 142, the operation detection unit 143, the recognition control unit 144, and the output control unit 146. May be present.

  Further, the effects described in the present specification are merely illustrative or exemplary and are not limited. That is, the technology according to the present disclosure can exhibit other effects that are apparent to those skilled in the art from the description of the present specification in addition to or instead of the above effects.

The following configurations also belong to the technical scope of the present disclosure.
(1)
An output control unit that causes the output unit to output a start condition of voice recognition processing performed by the voice recognition unit on the sound information input from the sound collecting unit;
The output control unit dynamically changes the start condition of the voice recognition processing to be output to the output unit;
Information processing system.
(2)
The output control unit causes the output unit to output the start condition when a start trigger of the voice recognition process is detected.
The information processing system according to (1).
(3)
The information processing system includes a recognition control unit that causes the voice recognition unit to start the voice recognition processing when the start condition is satisfied.
The information processing system according to (1) or (2).
(4)
The output control unit stops the output of the start condition when the start condition is satisfied or when an output stop operation of the start condition is detected,
The information processing system according to any one of (1) to (3).
(5)
The output control unit dynamically changes the start condition of the voice recognition processing to be output to the output unit based on predetermined information.
The information processing system according to (2).
(6)
The output control unit dynamically changes the start condition to be output to the output unit based on sound information input from the sound collection unit after the activation trigger is detected.
The information processing system according to (5) above.
(7)
The output control unit dynamically changes the start condition to be output to the output unit based on the first type of sound information included in the sound information input from the sound collection unit.
The information processing system according to (6).
(8)
The output control unit changes the start condition to information related to a user operation necessary to start the voice recognition process when the volume of the first type of sound information exceeds a first threshold.
The information processing system according to (7).
(9)
The output control unit changes the start condition to a remaining time until the voice recognition process is started when a volume of the first type of sound information is lower than the first threshold.
The information processing system according to (8).
(10)
The output control unit omits outputting the start condition to the output unit when the volume of the sound information of the first type is lower than a second threshold value that is smaller than the first threshold value;
The information processing system according to (8) or (9).
(11)
The first type of sound information includes at least noise.
The information processing system according to any one of (7) to (10).
(12)
The output control unit sets the start condition to be output to the output unit based on past sound information collected at a predetermined time from when the activation trigger is detected in the past to when the voice recognition process is started. Change dynamically,
The information processing system according to (6).
(13)
The output control unit dynamically changes the start condition to be output to the output unit based on the second type of sound information included in the past sound information.
The information processing system according to (12).
(14)
When the volume of the second type of sound information exceeds a threshold, the output control unit determines the remaining time until the voice recognition process to be output as the start condition is started at the time of the previous voice recognition process. Longer than,
The information processing system according to (13).
(15)
When the volume of the second type of sound information is lower than the threshold, the output control unit uses the remaining time until the voice recognition process to be output as the start condition is started as the previous voice recognition process. Shorter than time,
The information processing system according to (14).
(16)
The second type of sound information includes at least noise.
The information processing system according to any one of (13) to (15).
(17)
The output control unit dynamically changes the start condition to be output to the output unit based on the number of arrival directions of sound information whose sound quality exceeds a threshold value to the sound collection unit.
The information processing system according to (1).
(18)
The output control unit causes the output unit to output at least one of predetermined display information and predetermined audio information as the start condition.
The information processing system according to any one of (1) to (17).
(19)
The recognition control unit starts speech recognition processing before the start condition is satisfied, and when the start condition is satisfied, if the filler is included in the result of the speech recognition processing, it corresponds to the filler. Causing the voice recognition unit to start voice recognition processing on the sound information after the part to be removed is excluded.
The information processing system according to (3).
(20)
Including causing the output unit to output a start condition of voice recognition processing performed by the voice recognition unit on the sound information input from the sound collection unit,
Dynamically changing the start condition of the speech recognition process to be output to the output unit by a processor;
Information processing method.

DESCRIPTION OF SYMBOLS 120 Sound collecting part 10 Information processing system 110 Image input part 115 Operation input part 130 Output part 140 Information processing apparatus (control part)
141 Input Image Acquisition Unit 142 Sound Information Acquisition Unit 143 Operation Detection Unit 144 Recognition Control Unit 145 Speech Recognition Unit 146 Output Control Unit G10 Initial Screen G11 Recognition Character String Display Field G12 All Delete Operation Object G13 Confirmation Operation Object G15 Forward Movement Operation Object G16 Backward movement operation object G17 Deletion operation object

Claims (20)

An output control unit that causes the output unit to output a start condition of voice recognition processing performed by the voice recognition unit on the sound information input from the sound collecting unit;
The output control unit dynamically changes the start condition of the voice recognition processing to be output to the output unit;
Information processing system. The output control unit causes the output unit to output the start condition when a start trigger of the voice recognition process is detected.
The information processing system according to claim 1. The information processing system includes a recognition control unit that causes the voice recognition unit to start the voice recognition processing when the start condition is satisfied.
The information processing system according to claim 1. The output control unit stops the output of the start condition when the start condition is satisfied or when an output stop operation of the start condition is detected,
The information processing system according to claim 1. The output control unit dynamically changes the start condition of the voice recognition processing to be output to the output unit based on predetermined information.
The information processing system according to claim 2. The output control unit dynamically changes the start condition to be output to the output unit based on sound information input from the sound collection unit after the activation trigger is detected.
The information processing system according to claim 5. The output control unit dynamically changes the start condition to be output to the output unit based on the first type of sound information included in the sound information input from the sound collection unit.
The information processing system according to claim 6. The output control unit changes the start condition to information related to a user operation necessary to start the voice recognition process when the volume of the first type of sound information exceeds a first threshold.
The information processing system according to claim 7. The output control unit changes the start condition to a remaining time until the voice recognition process is started when a volume of the first type of sound information is lower than the first threshold.
The information processing system according to claim 8. The output control unit omits outputting the start condition to the output unit when the volume of the sound information of the first type is lower than a second threshold value that is smaller than the first threshold value;
The information processing system according to claim 8. The first type of sound information includes at least noise.
The information processing system according to claim 7. The output control unit sets the start condition to be output to the output unit based on past sound information collected at a predetermined time from when the activation trigger is detected in the past to when the voice recognition process is started. Change dynamically,
The information processing system according to claim 6. The output control unit dynamically changes the start condition to be output to the output unit based on the second type of sound information included in the past sound information.
The information processing system according to claim 12. When the volume of the second type of sound information exceeds a threshold, the output control unit determines the remaining time until the voice recognition process to be output as the start condition is started at the time of the previous voice recognition process. Longer than,
The information processing system according to claim 13. When the volume of the second type of sound information is lower than the threshold, the output control unit uses the remaining time until the voice recognition process to be output as the start condition is started as the previous voice recognition process. Shorter than time,
The information processing system according to claim 14. The second type of sound information includes at least noise.
The information processing system according to claim 13. The output control unit dynamically changes the start condition to be output to the output unit based on the number of arrival directions of sound information whose sound quality exceeds a threshold value to the sound collection unit.
The information processing system according to claim 1. The output control unit causes the output unit to output at least one of predetermined display information and predetermined audio information as the start condition.
The information processing system according to claim 1. The recognition control unit starts speech recognition processing before the start condition is satisfied, and when the start condition is satisfied, if the filler is included in the result of the speech recognition processing, it corresponds to the filler. Causing the voice recognition unit to start voice recognition processing on the sound information after the part to be removed is excluded.
The information processing system according to claim 3. Including causing the output unit to output a start condition of voice recognition processing performed by the voice recognition unit on the sound information input from the sound collection unit,
Dynamically changing the start condition of the speech recognition process to be output to the output unit by a processor;
Information processing method.

Images