JP3588975B2 - Voice input device - Google Patents

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a speech input device capable of performing large vocabulary recognition with a small number of inputs.
[0002]
[Prior art]
2. Description of the Related Art Voice input devices that recognize voice and read information can input commands, data, and the like without using hands, and thus are being used in places where manual operations are difficult, such as word processors for disabled persons and in-vehicle navigation.
As shown in FIG. 13, a typical voice input device includes a microphone 500 that captures voice and converts it into an electric signal and outputs a voice signal, and an A / D converter that converts an analog voice signal into digital information by A / D conversion. / D converter 501, an external storage device 503 storing a word dictionary used for performing word recognition from a voice signal, a CPU and a memory, and having the word dictionary read into the memory. And a signal processing device 502 that performs voice recognition by determining the degree of coincidence with the word.
The switch 505 is operated by the user of the apparatus and gives the timing of capturing the audio signal to the signal processing apparatus 502. The monitor 504 displays the recognized word.
[0003]
In general, in the case of speech input, the recognition rate decreases as the number of words to be recognized increases, and a hierarchical dictionary is used for large vocabulary recognition. At the time of input, voice input is repeated a plurality of times in accordance with the dictionary classification, the hierarchy is advanced, recognition is performed in a state where the number of words to be recognized is narrowed down, and the erroneous recognition rate is reduced.
[0004]
Details of the speech recognition in the above-described conventional device will be described with reference to the flowchart of FIG.
Here, a case where "Sakuragicho" which is the station name of JR is input by voice is shown. Such a station name input is used for setting a destination of a navigation device of an automobile. The external storage device 503 stores a hierarchical word dictionary as shown in FIG. 2, for example.
[0005]
First, in step 521, in the initial state of voice input, the signal processing device 502 sets a partial dictionary at the highest level of the hierarchical word dictionary as a first recognition target. Here, the partial dictionary a in FIG. 2 is set.
Next, the device user operates the switch 505 to speak “facility” to the microphone 500. This is because the user has recognized that “Sakuragicho” is included in the category of “facility”.
The operation of the switch 505 is detected in step 522. Thereby, the voice recognition processing is started.
[0006]
In step 523, the CPU in the signal processing device 502 reads the partial dictionary of the set hierarchy from the external storage device 503 into the memory. Initially, the partial dictionary a is read.
The signal processing device 502 calculates the average power of the sound until the switch 505 is operated, and after the switch 505 is operated, the instantaneous power of the sound signal becomes larger than the average power of the sound by a predetermined value or more. Then, it is determined that the user has started uttering, and voice capture is started in step 524.
[0007]
In step 525, the CPU calculates the degree of coincidence between the input voice and the word in the partial dictionary read into the memory. Initially, the degree of coincidence with each of “address” and “facility” is calculated.
[0008]
When the instantaneous power of the audio signal becomes equal to or less than the predetermined value, it is determined that the utterance of the user has ended, and in step 526, the capturing of the audio is ended.
When the calculation of the degree of matching between the input voice and the word in the partial dictionary is completed, in step 527, the CPU selects the word having the highest degree of matching. Here, "facility" is selected because the degree of coincidence is higher.
[0009]
In step 528, the selected word having a high degree of matching is displayed on the monitor 504 as a result of the recognition.
In step 529, it is determined whether or not the selected word is a partial dictionary name of a lower hierarchy. If the selected word is a dictionary name, the process proceeds to step 523; otherwise, the process proceeds to step 530. Here, since the word “facility” is the dictionary name of the partial dictionary e in the lower hierarchy as shown in the word dictionary of FIG. 2, the process returns to step 523.
[0010]
In step 523, the CPU newly reads the partial dictionary e from the external storage device 503 into the memory. In this way, the hierarchy advances each time the processing is repeated. When there is no partial dictionary under the selected word, in step 530, the recognized word is output as an object. Here, "Sakuragicho" is output.
[0011]
[Problems to be solved by the invention]
As described above, in the conventional voice input device, to transmit one word, the partial dictionary names up to the lowest layer to which the word belongs must be input for each layer. Since the hierarchy becomes more complicated as the number of words increases, there is a problem in that the recognition load from the large vocabulary increases the user's input burden. Further, there is a problem that although the user wants to convey the object most, the input of the object lasts a sense of incongruity at the end and is not easy to use.
The present invention has been made in view of the above-described conventional problems, and has as its object to realize accurate voice input with a small number of input times.
[0012]
[Means for Solving the Problems]
Voice input means for converting the uttered voice into information and inputting the information;
A word dictionary consisting of a partial dictionary including a plurality of words and having a hierarchical structure,
Means for determining a partial dictionary to be used;,
Calculating means for calculating the degree of coincidence between the input voice from the voice input means and the word in the determined partial dictionary;
Word selecting means for selecting and outputting the word having the highest matching degree among the calculated words,
The partial dictionary determining means first determines a predetermined lowermost partial dictionary,When an instruction to change to a higher hierarchy is received, a partial dictionary of the specified upper hierarchy is determined, the input dictionary is changed to the hierarchy indicated by the word selected by the word selecting means, and a predetermined lower hierarchy below the hierarchy is determined.A partial dictionary was determined.
[0013]
It is preferable that the partial dictionary first determined by the partial dictionary determining means is the lowest partial dictionary used last time.
It is also possible to use a lower-level partial dictionary frequently used in place of the lowest-level partial dictionary used last time.
[0014]
It is desirable that display means is connected to the voice input device to display the word selected by the word selection means and the upper hierarchical structure.
The display unit may have a touch panel and output a hierarchy change command corresponding to the hierarchy touched by the user to the partial dictionary determination unit.
Further, it is desirable to display a changeable hierarchy on the display means when a touch input is made on the touch panel.
[0015]
The partial dictionary determination means determines that, when an input is made following the object, an instruction to change to a higher hierarchy is received, and all partial dictionaries higher than the set lowermost partial dictionary are determined. The hierarchy can be changed to the hierarchy indicated by the word selected by the selection means.
[0016]
The sub-dictionary deciding means, when an input is made following the object, decides the set lowest sub-dictionary and all sub-dictionaries higher than the set sub-dictionary, and the word selected by the word selecting means is set If the word is in the dictionary, it is assumed that a change instruction to a higher hierarchy has been received, and the hierarchy can be changed to the hierarchy indicated by the word.
[0017]
In addition, when the hierarchy is changed, the word selecting means uses the voice stored in the storage means to store the first input speech in the determined partial dictionary. Can be calculated and output.
[0018]
[Action]
When a hierarchical dictionary is used and a partial dictionary is set, a predetermined lowermost partial dictionary is first set, so that large vocabulary recognition can be performed and the first word can be used as an object. . If it cannot be recognized by one input, the hierarchy is changed by the hierarchy change command, so for example, change to the upper hierarchy common to the current partial dictionary and the partial dictionary with the object, and determine the lowest partial dictionary This eliminates the need for input from the uppermost partial dictionary, thereby achieving efficient input. Further, since the input is performed from the beginning with the object and the change in the hierarchy of the dictionary cannot be recognized, the voice input matching the sense can be performed.
[0019]
The partial dictionary determining means, when receiving an instruction to change to a higher hierarchical level, determines a partial dictionary of the upper hierarchical level, changes to a hierarchical level indicated by the word selected by the word selecting means by input, and determines a predetermined lowermost hierarchical level below the hierarchical level. If a partial dictionary is determined, there is a hierarchy change.handAlso, it is not necessary to recognize the partial dictionary between the partial dictionary of the object and the upper hierarchy, and even if the hierarchy is changed to a higher hierarchy, the object is input immediately, so that the input is performed without frustrating the device user. The effect that can be obtained is obtained.
Further, if the partial dictionary determined first by the partial dictionary determining means is the lowest partial dictionary used last time, the dictionary configuration can be understood and the hierarchy can be changed smoothly.
Further, the same effect can be obtained by using a lower-level partial dictionary frequently used in place of the lowest-level partial dictionary used last time.
[0020]
When the display means is connected to the voice input device and the word selected by the word selection means and the upper hierarchical structure are displayed on the display means, when the hierarchy needs to be changed, the hierarchy is changed based on the displayed hierarchical structure. , The input burden is reduced.
If the display unit has a touch panel and outputs a hierarchy change command corresponding to the hierarchy touched by the user to the partial dictionary determination unit, the input becomes interactive and the input load is further reduced.
Further, when a hierarchy that can be changed by voice input is displayed on the display unit when there is a touch input, the structure of the dictionary can be known from the display screen, and even if there is no prior knowledge such as the configuration of the dictionary. The effect that the hierarchy can be changed is obtained.
[0021]
When the input is performed following the object, the partial dictionary determining means determines that an instruction to change to a higher hierarchical level is received, determines all partial dictionaries higher than the set lowest partial dictionary, and If the hierarchy is changed to the hierarchy indicated by the word selected by the selecting means, the hierarchy can be changed only by the words in the upper hierarchy, and the input load can be further reduced.
[0022]
The sub-dictionary deciding means, when an input is made following the object, decides the set lowest sub-dictionary and all sub-dictionaries higher than the set sub-dictionary, and the word selected by the word selecting means is set If it is a word in the dictionary, it is assumed that a change instruction to a higher hierarchy has been received, and if the hierarchy is changed to the hierarchy indicated by the word, the hierarchy change due to incorrect recognition of the word is prevented while the partial dictionary is accurate. You.
[0023]
When the hierarchy is changed, the word selection means uses the speech stored in the storage means to store a word in the lowermost partial dictionary determined when the hierarchy is changed. By calculating and outputting the degree of coincidence with, even if the hierarchy is changed and the partial dictionary at the lowest level is changed, it is not necessary to input the speech of the object word again, and the number of times of inputting the speech is further reduced.
[0024]
BEST MODE FOR CARRYING OUT THE INVENTION
Next, embodiments of the present invention will be described with reference to examples.
FIG. 1 is a block diagram showing the configuration of the first embodiment of the present invention.
The audio signal captured by the microphone 500 is converted into digital information by the A / D converter 501 and input to the signal processing device 5. The switch 505 is operated just before the device user speaks for voice input, and gives the signal processing device 5 a detection timing of the speech voice. The external storage device 503 stores a word dictionary. The monitor 60 is a monitor with a touch panel, which displays the processing results of the signal processing device 5 and allows the partial dictionary to be changed using the touch panel.
[0025]
As the word dictionary, a hierarchical word dictionary as shown in FIG. 2 is used. In the figure, the connecting lines between the partial dictionaries indicate the connection relationship between the upper and lower layers, and what protrudes in the frame is the display of words representing the lower hierarchy.
The partial dictionary a composed of two words “address” and “facility” is located at the top level of the word dictionary. Each word is a lower-level dictionary. A partial dictionary b is provided, and a partial dictionary c in which city and ward names are written and a partial dictionary d in which ward and village names are written are sequentially provided for each prefecture.
[0026]
Below the word “facility” in the partial dictionary a, a partial dictionary e of words describing the type names of “facility” such as “station”, “department store”, and “hotel” follows. A partial dictionary f in which the names of prefectures are described below “station” is provided. From the partial dictionary f, a partial dictionary g describing a transportation company name and a partial dictionary h of a station name connected to the partial dictionary g are provided for each prefecture.
[0027]
The word "department store" also has a lower-level partial dictionary i describing the name of the prefecture, a partial dictionary j describing the name of the city, and a partial dictionary k describing the name of the "department store". It is linked to a dictionary and a sub-dictionary of the ward.
The partial dictionary d, the partial dictionary h, and the partial dictionary k are the lowest-level partial dictionaries, in which object words are registered, and words to be recognized are collated and recognized here.
[0028]
The signal processing device 5 calculates the average power of the audio signal digitized from the microphone 500 until the switch 505 is operated in the audio input unit 53. When the instantaneous power becomes larger than the average power value, it is determined that the utterance has started, and the capture of the audio signal is started. The voice signal is word-recognized in the word selection unit 52. At this time, the word dictionary used first is the partial dictionary in the lowest hierarchy read by the partial dictionary determination unit 51 from the external storage device 503.
[0029]
The word output unit 54 temporarily outputs the result of the recognition and the name of the upper layer of the word to the monitor 60, but suspends the output as the device. During this time, the partial dictionary can be changed by touch-inputting the name of the upper hierarchy displayed on the monitor 60. If there is no touch on the touch panel within a predetermined time, the word output unit 54 outputs the recognition result as an output of the device.
[0030]
When there is a change in the partial dictionary, the partial dictionary determination unit 51 reads the partial dictionary of the touched name from the external storage device 503, and the device user operates the switch 505 to give an utterance for determining the lower dictionary. I do. The partial dictionary determining section 51 determines a predetermined lowest-order partial dictionary relating to the partial dictionary and reads it from the external storage device 503. Thereafter, voice input is performed again, and word recognition is performed in the word selection unit 52.
The lowest partial dictionary input first or input after changing the hierarchy is the partial dictionary used last time or the most frequently used partial dictionary.
[0031]
Next, the operation flow of the apparatus will be described with reference to the flowchart of FIG.
First, in step 101, in the initial state of voice input, the partial dictionary determination unit 51 sets the lowest partial dictionary in the hierarchy as the first recognition target. The most frequently used partial dictionary or the lowest partial dictionary used last time is used as the initial setting. Here, for example, it is assumed that the partial dictionary h in FIG. 2 is set.
[0032]
The user of the device operates the switch 505 to speak into the microphone 500.
In step 102, the voice input unit 53 detects whether or not the switch 505 has been operated. If the switch 505 has been operated, the average power value of the voice after the microphone 500 has been operated is calculated, and the process proceeds to step 103.
In step 103, the determined partial dictionary is read from the external storage device 503 into the partial dictionary determination unit 51. Here, the partial dictionary h is read.
[0033]
In step 104, the utterance voice of the user is started. That is, when the instantaneous power becomes greater than a predetermined value compared to the average power of the voice which is constantly calculated from the input voice signal, it is determined that the user's utterance has started, and the capturing of the utterance voice is started.
Here, for example, it is assumed that the user has spoken “Sakuragicho” as the object.
In step 105, the word selection unit 52 calculates the degree of coincidence between the word in the partial dictionary h read by the partial dictionary determination unit 51 and the uttered voice. In this process, a speech section portion divided by a predetermined time is compared with each word while taking a speech signal, and the acquisition of the speech signal is proceeding at the same time.
[0034]
When the instantaneous power of the audio signal becomes equal to or less than the average power in step 106, the user determines that the utterance is completed, ends the voice capturing, and proceeds to step 107.
In step 107, the word having the highest matching degree calculated by the word selection unit 52 is output to the word output unit 54 as a recognition result.
[0035]
In step 108, the word output unit 54 temporarily outputs the recognition result and the name of the upper layer of the word to the monitor 60 for display, but suspends the output as a device. FIG. 4 shows a display screen of the monitor 60. h is a dictionary of the selected word, and a, e, f, and g are high-order dictionaries of the word. The object displayed from the h frame is the object, and the words arranged in the upper frame are words in the upper dictionary related to the object, and the hierarchical order is displayed from right to left. I have. When changing the hierarchy, the user can touch the place where the word is displayed to change the hierarchy.
Then, in step 109, if there is no touch input on the touch panel within a predetermined time, in step 110, the recognition result of the word "Sakuragicho" is output as an output of the apparatus.
In this case, there is no need to change the hierarchy, and the number of utterances ends once.
[0036]
If the user uttered “Sougo” in step 104, another word would be displayed because the initial partial dictionary was h. In this case, since it is necessary to change the upper hierarchy, the user touches e in FIG.
[0037]
When the touch input is detected in step 109, the process proceeds to step 111.
In step 111, the monitor 60 displays which layer the touched layer can be changed to. Here, "station", "department store", and "hotel" are displayed. FIG. 5 shows the display state.
In step 112, the partial dictionary determination unit 51 newly reads the partial dictionary e from the external storage device 503.
[0038]
In step 113, the user touches and selects from the displayed upper hierarchy to input a voice. In the case of “Sougo”, the user inputs “Department store” related thereto by voice and is recognized by the word selection unit 52. In this step, the same processing as steps 102 to 107 may be performed.
In step 114, the partial dictionary determination unit 51 determines the lowest partial dictionary k connected to the recognized word “department”.
[0039]
In step 115, an input instruction mark is displayed again on the monitor 60 to notify the user of the voice input retry again, and the process returns to step 102.
Thereafter, the user utters “SOGO”, and the processing from step 102 to step 108 is performed again. In step 110, the word “SOGO” is output.
[0040]
The microphone 500, the A / D converter 501, and the audio input unit 53 constitute an audio input unit. The partial dictionary determination section 51 constitutes a dictionary determination unit. The word selecting section 52 constitutes word selecting means. The monitor 60 constitutes a display unit.
[0041]
The present embodiment is configured as described above. When the first speech is input, the degree of coincidence between the speech signal and a word in the predetermined lowermost partial dictionary is calculated. It can be used as an object, and the user's input burden is reduced. Further, when a partial dictionary needs to be changed, even if there are a plurality of hierarchies below the higher hierarchy, the lowest partial dictionary is set and used.
Then, since the partial dictionary used first is the one used frequently or the one used last time, the user can easily understand the output result and smoothly change the hierarchy.
[0042]
In addition, since the monitor displays the hierarchical structure of the word when the word is displayed, it is possible to easily determine which layer the user wants to change.
When there is a touch input, by displaying what level can be changed by voice input, it is possible to perform an operation to change to which level without knowing the dictionary configuration.
[0043]
FIG. 6 is a block diagram showing the configuration of the second embodiment.
In this embodiment, a signal processing device 6 provided with an audio storage unit 66 is used instead of the signal processing device 5 in the first embodiment shown in FIG. The voice signal storage unit 66 outputs the voice signal of the voice input unit 63 to the word selection unit 62, and stores the first voice signal in the voice storage unit 66. When the partial dictionary is changed, the degree of coincidence with the partial dictionary is determined using the voice signal stored in the voice storage unit 66, and the object is recognized. Others are the same as the first embodiment.
[0044]
Next, the operation flow of the apparatus will be described with reference to the flowchart of FIG.
In steps 201 to 215, the same processes as those in steps 101 to 114 of the flowchart of FIG. 3 in the first embodiment are performed except for step 207.
That is, first, the partial dictionary at the lowest level of the hierarchy is set as the first recognition target, and is read from the external storage device 503. While fetching the user's utterance voice signal, a word in the set partial dictionary and the degree of coincidence are calculated. Then, when the capture of the audio signal is completed, in step 207, the audio storage unit 66 stores the audio signal.
The word having the highest matching degree is selected as a result of the recognition, and is displayed on the monitor 60 including the upper hierarchy.
[0045]
Then, if there is no touch input on the touch panel of the monitor 60 within a predetermined time, the selected word is output as an output of the apparatus. If there is a touch input, the partial dictionary is changed to the touched hierarchy. The partial dictionary whose hierarchy has been changed is newly read from the external storage device 503. Thereafter, an utterance for changing the hierarchy is made, and when a word indicating the hierarchy is specified by voice input, the lowest partial dictionary under the hierarchy is read from the external storage device 503.
[0046]
Thereafter, in the first embodiment, the user is notified again of the re-input of the voice, but in the present embodiment, in step 216, the voice signal stored from the voice storage unit 66 is used, and the word in the lowermost partial dictionary is used. Is calculated. From each word, the word with the highest degree of matching is selected in step 208. If it is determined in step 210 that there is no touch input to the monitor 60, the word recognized in step 211 is output as an output of the device.
[0047]
According to this embodiment, the same effect as that of the first embodiment can be obtained, and it is not necessary to first speak and input the object again after the partial dictionary is changed. Become.
[0048]
Next, a third embodiment will be described.
FIG. 8 is a block diagram showing the configuration of the third embodiment.
In this embodiment, a signal processing device 7 is used instead of the signal processing device 6 in the second embodiment shown in FIG. The voice signal storage unit 66 outputs the voice signal of the voice input unit 73 to the word selection unit 62, and stores the first voice signal in the voice storage unit 66. If there is a partial dictionary change, it is recognized using the voice signal stored in the voice storage unit 66.
[0049]
In the first or second embodiment, the hierarchy is changed by the touch panel of the monitor 60. In this embodiment, the hierarchy is changed by voice. That is, the first and second embodiments are different from the first and second embodiments in that the first speech input corresponds to the object and the subsequent speech inputs correspond to the hierarchy change. Instead of the monitor 60, a monitor 70 for displaying only is used. Others are the same as the first embodiment.
[0050]
Next, the operation flow of the apparatus will be described with reference to the flowchart of FIG.
In steps 201 to 216, the same processes as those in the flowchart of FIG. 7 in the second embodiment are performed except for steps 310 and 313.
That is, first, the lowest partial dictionary in the hierarchy is set as the first recognition target, and is read from the external storage device 503. While fetching the user's utterance voice signal, a word in the set partial dictionary and the degree of coincidence are calculated. When the capture of the audio signal ends, the audio storage unit 66 stores the audio signal.
Then, in step 208, the word having the highest degree of matching is selected as a result of the recognition.
[0051]
In step 310, the voice input unit 73 detects whether or not the switch 505 has been operated. If the switch 505 has been operated, the process proceeds to step 313 because there is a voice input.
In step 313, all the partial dictionaries higher than the currently used partial dictionary are read from the external storage device 503.
After that, as in the first and second embodiments, voice input of the upper hierarchy is performed, and when a word indicating the hierarchy is specified, the lowest partial dictionary under the hierarchy is read from the external storage device 503.
[0052]
In step 216, the degree of coincidence with a word in the partial dictionary is calculated using the voice signal stored from the voice storage unit 66. From each word, the word with the highest degree of matching is selected in step 208.
If it is detected in step 310 that there is no operation on the switch 505, the word recognized in step 211 is output as an output of the device.
In this way, for example, when the partial dictionary h is initially set and the word to be input is “Sougo” that is not in the dictionary, if the user speaks “Department store”, the “Sougo” as shown in FIG. Since the hatched partial dictionaries including the upper dictionary are automatically set, there is no troublesome operation even if there is a hierarchy change.
[0053]
That is, when the device outputs words of a different hierarchy from the hierarchy specified by the user in response to the first utterance, the user utters the hierarchy name desired by the user, and the utterance, reply, and detailed explanation are taken. A natural dialogue can be realized, and an effect that voice input can be performed with the most natural feeling can be obtained.
Since the partial dictionaries of each layer are set, there is a concern that the recognition rate may decrease due to speech.However, words in the upper partial dictionary are generally words for classification, and the number of words is in the lowest partial dictionary. Since the number of words is extremely small compared to the number of words, the recognition rate is sufficient for use.
[0054]
Next, a modification of the third embodiment will be described.
In each of the above embodiments, even if the partial dictionary at the lowest level is set correctly, words may be erroneously recognized due to the influence of noise or the like. In this case, even if the partial dictionaries of all the upper hierarchies are reset, the original partial dictionary is reached, which results in an unnecessary number of times of input. This modification is intended to deal with such a case, and even if there is an erroneous recognition, words in the same partial dictionary can be processed without changing the hierarchy.
[0055]
FIG. 11 is a flowchart showing the flow of the operation of the apparatus.
This flowchart is configured by replacing Steps 412, 413, and 414 with Steps 313 and 214 in the third embodiment of FIG.
That is, first, the lowest partial dictionary in the hierarchy is set as the first recognition target, and is read from the external storage device 503. A word in the set partial dictionary and the degree of coincidence are calculated while taking the user's speech signal. When the capture of the audio signal ends, the audio storage unit 66 stores the audio signal.
The word having the highest degree of matching is selected as a result of recognition, and is displayed on the monitor 70 including the upper layer in step 209.
[0056]
Then, in step 310, the voice input unit 73 detects whether or not the switch 505 has been operated. If the switch 505 has been operated, the process proceeds to step 412 because there is a voice input.
In step 412, the currently used partial dictionary and all partial dictionaries thereof are read.
In step 413, the voice spoken by the user is input, and the degree of coincidence with the read word in the partial dictionary is calculated.
[0057]
In step 414, it is determined whether or not the word having the highest degree of coincidence exists in the partial dictionary in the upper hierarchy. If the word is in the partial dictionary of the upper hierarchy, it is for changing the hierarchy, and the process proceeds to step 215 to perform the same processing as in the third embodiment. If the word is in the lowermost partial dictionary, the process proceeds to step 209 because it is a recognized object, and the word is output in step 211 after determining in step 310 whether a new operation has been performed on the switch. Is done.
[0058]
In this way, if the partial dictionary h is initially set and the word to be input is "Sakuragicho", the sound signal of "Sakuragicho" is distorted due to noise or the like, and is incorrectly displayed as "Kannai". May be It is also conceivable that the user intends to utter "Sakuragicho" and erroneously utters "Kannai". Even if such a partial dictionary is correct, all upper-layer partial dictionaries including the partial dictionary h are automatically set, as indicated by hatching in FIG. 12, so if "Sakuragicho" is re-uttered, Voice input without changing the hierarchy. As a result, the hierarchy is changed only when necessary, and the voice input burden is further reduced. In addition, as in the third embodiment, there is also obtained an effect that a voice can be input in a natural dialogue style such as utterance, reply, and detailed explanation.
[0059]
【The invention's effect】
As described above, according to the present invention, the first word can be used as the object. Therefore, the object is first input, and if it is not correct, the hierarchy is changed and the object is input again to recognize the object. And you can input speech with a natural feeling. Also, when changing a dictionary, for example, it is necessary to go back from the current partial dictionary and change to a higher partial dictionary with the same content as the object and determine the lowest partial dictionary. Fewer inputs and less typing
[0060]
The partial dictionary determining means, when receiving an instruction to change to a higher hierarchy, determines a partial dictionary in the upper hierarchy, changes to a hierarchy indicated by the word selected by the word selecting means by voice input, and determines a predetermined lower hierarchy in the hierarchy. When the lower-level partial dictionary is determined, there is no need to recognize the partial dictionary up to the partial dictionary containing the object even if the hierarchy is changed, and an effect of not causing a large input load can be obtained.
Further, if the partial dictionary determined first by the partial dictionary determining means is the lowest partial dictionary used last time, the dictionary configuration can be understood and the hierarchy can be changed smoothly.
Further, the same effect can be obtained by using a lower-level partial dictionary frequently used in place of the lowest-level partial dictionary used last time.
[0061]
When the display means is connected to the voice input device and the word selected by the word selection means and the upper hierarchical structure are displayed on the display means, when the hierarchy needs to be changed, the hierarchy is changed based on the displayed hierarchical structure. Therefore, the input load can be further reduced.
If the display means has a touch panel and outputs a hierarchy change command corresponding to the hierarchy touched by the user to the partial dictionary determination unit, the input becomes interactive and the input load is further reduced.
In addition, when a touch input is performed and a hierarchy that can be changed by voice input is displayed on the display unit, the structure of the dictionary can be known from the display screen, and the hierarchy can be changed without prior knowledge of the dictionary configuration. The effect that can be obtained is obtained.
[0062]
The partial dictionary determination means, when a speech input is performed following the object, determines that a change instruction to a higher hierarchy has been received, and determines all partial dictionaries higher than the set lowermost partial dictionary, When the hierarchy is changed to the hierarchy indicated by the word selected by the word selecting means, the operation for changing the hierarchy is unnecessary, and the input load is further reduced.
[0063]
The sub-dictionary deciding means decides the lowermost sub-dictionary set and all the sub-dictionaries higher than the set sub-dictionary when the speech input is performed following the object, and the word selected by the word selecting means is higher If it is a word in the partial dictionary, it is assumed that a change instruction to a higher hierarchical level has been received, and if the hierarchical level is changed to the hierarchical level indicated by the word, the hierarchical change due to incorrect recognition of the word is prevented while the partial dictionary is accurate. Thus, an effect of not causing useless input can be obtained.
[0064]
When the hierarchy is changed, the word selection means uses the speech stored in the storage means to store a word in the lowermost partial dictionary determined when the hierarchy is changed. By calculating and outputting the degree of coincidence with the subject, even if the hierarchy is changed and the partial dictionary at the lowest level is changed, there is no need to input the speech of the object again, and the number of times of speech input is further reduced. In addition, when the device outputs words of a different hierarchy from the hierarchy that the user wants to specify for the first utterance, a procedure is adopted in which the user utters the hierarchy name that the user wants to specify, as in the second embodiment. , Utterance, reply, and detailed explanation can be realized, and the effect of inputting voice with the most natural feeling can be obtained.
[Brief description of the drawings]
FIG. 1 is a block diagram illustrating a configuration of a first embodiment.
FIG. 2 is a diagram showing a configuration of a hierarchical word dictionary.
FIG. 3 is a flowchart of the first embodiment.
FIG. 4 is a block diagram showing a monitor display screen.
FIG. 5 is a diagram showing a monitor display screen when a partial dictionary is changed.
FIG. 6 is a block diagram showing a configuration of a second embodiment.
FIG. 7 is a flowchart of the second embodiment.
FIG. 8 is a block diagram illustrating a configuration of a third embodiment.
FIG. 9 is a flowchart of the third embodiment.
FIG. 10 is a diagram illustrating an upper partial dictionary temporarily set when the lowermost partial dictionary is changed.
FIG. 11 is a flowchart showing a modification of the third embodiment.
FIG. 12 is a diagram illustrating a partial dictionary temporarily set when the lowest partial dictionary is changed.
FIG. 13 is a block diagram showing a configuration of a conventional example.
FIG. 14 is a flowchart of a conventional example.
[Explanation of symbols]
5, 6, 7 signal processing device
51, 71 partial dictionary determination unit
52, 62 Word selector
53, 63, 73 Voice input unit
54, 64 word output unit
60, 70, 504 monitor
66 Voice storage unit
500 microphone
501 A / D converter
502 signal processing device
503 External storage device
505 switch
a, b, c, d, e, f partial dictionary
g, h, i, j, k partial dictionary

Claims (9)

Voice input means for converting the uttered voice into information and inputting the information;
A word dictionary consisting of a partial dictionary including a plurality of words and having a hierarchical structure,
A partial dictionary determining means for determining a partial dictionary to be used ;
Calculating means for calculating the degree of coincidence between the voice information from the voice input means and the word in the determined partial dictionary;
Word selecting means for selecting and outputting the word having the highest matching degree among the calculated words,
The partial dictionary determining means first determines a predetermined lower-level partial dictionary, and when an instruction to change to a higher hierarchical level is received, determines a designated partial dictionary at an upper hierarchical level. A voice input device for changing to a hierarchy indicated by a selected word and determining a predetermined lowermost partial dictionary under the hierarchy . Voice input device according to claim 1, wherein the portion dictionaries that is determined at the beginning, characterized in lowermost portion dictionary der Rukoto the previously used by the partial dictionary determining means. 2. The voice input device according to claim 1, wherein the partial dictionary first determined by the partial dictionary determining means is a lower-most partial dictionary that is frequently used . 2. The voice input device according to claim 1 , wherein a display unit is connected to the voice input device, and the word selected by the word selection unit and an upper hierarchical structure are displayed . The voice input device according to claim 4, wherein the display unit has a touch panel, and a hierarchy change command corresponding to a hierarchy touched by a user is output to the partial dictionary determination unit . The display means when there is a touch input, a voice input device according to claim 5, wherein you to view a changeable hierarchy. The partial dictionary determination means determines that, when an input is made following the object, an instruction to change to a higher hierarchy is received, and all partial dictionaries higher than the set lowermost partial dictionary are determined. voice input device according to claim 1, characterized in that the hierarchy indicated by the word selecting means selects performing hierarchy changed. The sub-dictionary determining means, when an input is made following the object, determines the set lowest sub-dictionary and all sub-dictionaries higher than the set sub-dictionary. 2. The voice input device according to claim 1 , wherein if the word is in the dictionary, a change instruction to a higher hierarchy is received, and the hierarchy is changed to the hierarchy indicated by the word. The voice input device also has storage means for storing the first input voice signal, and when the hierarchy is changed, the word selection means uses the voice signal stored in the storage means to determine the most recently determined voice signal. calculates the degree of coincidence between words in the underlying portion dictionaries claim 1, 7 or voice input apparatus according 8, characterized in that the output.

Images