JP2002009963A - Communication system device and communication system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve the problem that video telephones are not widely spread in spite of their convenience because terminals loaded with cameras are required on both the sides of the conventional video telephone system, which causes problems of cost and portability. SOLUTION: A communication terminal is provided with a microphone 17, a voice recognition device 15 for receiving a voice signal from the microphone 17 and recognizing a voice, a mapping device 12a for collating the voice recognized by the voice recognition device 15 with a previously determined basic voice, a pseudo image data base 14 for storing pseudo picture data corresponding to the basic voice, a pseudo image acquiring device 12b for acquiring the pseudo picture data corresponding to the collated basic voice from the data base 14, and a communication control device 11 for transmitting the voice signal inputted from the microphone 17 and the pseudo image data to a specified communication terminal.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a communication terminal, a communication server, and a communication system using a pseudo image corresponding to an uttered sound.

[0002]

2. Description of the Related Art There are videophones that enable two-way communication by voice and image. A videophone includes a receiver including a microphone and a speaker, a camera for capturing an image of a person making a call, and a monitor for displaying a transmitted image. By using the videophone, the two parties making the call can have a conversation while seeing each other.

[0003]

However, in the above-described videophone, in order to have a conversation while confirming the other party's figure, it is necessary that both have a videophone equipped with a camera. In other words, in order to show yourself to the other party, you need a camera on the terminal you are using, and conversely, in order to see the other party, you need a camera on the terminal you are using. is there.

[0004] For this reason, the videophone inevitably has many components and the device configuration is relatively large. In addition, the cost is high due to the provision of a camera, and despite its high convenience, it has not yet become widespread.

[0005] Recently, portability is an important point for communication terminals. However, there is a problem that a videophone equipped with a camera has a large size to be carried around. In addition, since the camera is mounted, the cost also increases. Furthermore, in portable communication terminals (mobile phones) that are becoming more compact, it is necessary to reduce the number of components as much as possible, and mounting a camera is an obstacle.

[0006] Under the circumstances described above, there are many problems in disseminating a videophone equipped with a camera and having excellent portability, and as a result, a situation where the number of owners is small is caused. In other words, even if you have a videophone (regardless of stationary or portable type) capable of transmitting voice and image, the effect is not fully exhibited because the number of callers is limited. In the situation.

[0007] In a videophone, image data is transmitted and received in addition to audio, so that a heavy load is imposed on a communication line.

[0008] In view of the above problems, the present invention realizes a pseudo-telephone function to provide excellent portability.
Another object of the present invention is to provide a low-cost communication terminal.

[0009]

In order to solve the above-mentioned problems, the invention of claim 1 is an apparatus for a communication system which enables communication by voice and image, wherein the apparatus for a communication system is configured as a communication terminal. A communication terminal, a microphone for inputting voice, a voice recognition device for receiving voice signals from the microphone and recognizing voice, and a mapping for collating voice recognized by the voice recognition device with a predetermined basic voice. A device, a pseudo image database that stores pseudo image data corresponding to a predetermined basic sound, a pseudo image acquisition device that obtains pseudo image data corresponding to the collated basic sound from the pseudo image database, and a microphone. A communication system for transmitting an input audio signal and pseudo image data acquired by the pseudo image acquisition device to a designated communication destination terminal. Characterized in that it comprises apparatus and, a.

According to a second aspect of the present invention, there is provided an apparatus for a communication system capable of performing voice and image communication, wherein the apparatus for a communication system is configured as a communication terminal, and the communication terminal is transmitted from a communication destination terminal. A communication control device for receiving a voice signal, a voice recognition device for recognizing voice from a voice signal received by the communication control device, and a mapping for collating the voice recognized by the voice recognition device with a predetermined basic voice. A pseudo-image database for storing pseudo-image data corresponding to a predetermined basic sound, a pseudo-image acquiring device for obtaining pseudo image data corresponding to the collated basic sound from the pseudo-image database, and communication control. A speaker for reproducing the audio signal received by the device as audio, and a mode for outputting the pseudo image data acquired by the pseudo image acquisition device. Characterized in that it comprises data and, a.

According to a third aspect of the present invention, there is provided an apparatus for a communication system capable of performing communication by voice and image, wherein the apparatus for a communication system is configured as a communication server, and the communication server transmits from the communication terminal on the transmitting side. A receiving control device for receiving the received voice signal, a voice recognition device for recognizing voice from the voice signal received by the receiving control device, and collating the voice recognized by the voice recognition device with a predetermined basic voice. A mapping device, a pseudo image database that stores pseudo image data corresponding to a predetermined basic sound, a pseudo image acquisition device that obtains pseudo image data corresponding to the collated basic sound from the pseudo image database, A transmission control for transmitting an audio signal received by the control device and pseudo image data acquired by the pseudo image acquisition device to the transmission side communication terminal. Characterized in that it comprises apparatus and, a.

According to a fourth aspect of the present invention, in the communication system apparatus according to any one of the first to third aspects, the pseudo image data is video information including a facial expression of a person who utters a basic sound. It is characterized by the following.

According to a fifth aspect of the present invention, there is provided the communication system apparatus according to any one of the first to third aspects, wherein the pseudo image data represents video information representing a shape of a mouth of a person who utters a basic sound. It is characterized by being.

According to a sixth aspect of the present invention, in the communication system apparatus according to the fourth or fifth aspect, the pseudo image database stores a plurality of types of pseudo images having different backgrounds for the same basic sound. It is characterized by having data.

A seventh aspect of the present invention is the communication system apparatus according to any one of the fourth to sixth aspects, wherein the basic voice includes a combination of five vowels for a predetermined language, and the pseudo image database Comprises at least pseudo image data corresponding to each of the vowels.

According to an eighth aspect of the present invention, there is provided the communication system apparatus according to the seventh aspect, wherein the mapping apparatus has a function of comparing a vowel of the voice with a voice recognized by the voice recognition apparatus. .

According to a ninth aspect of the present invention, there is provided the communication system apparatus according to any one of the fourth to sixth aspects, wherein the basic voice includes five vowels and "n" sounds for Japanese, The image database is provided with at least pseudo image data corresponding to each of the vowels and the "n" sound.

According to a tenth aspect of the present invention, there is provided an apparatus for a communication system using the pseudo image according to the ninth aspect, wherein the mapping apparatus uses a voice recognized by the voice recognition apparatus other than the "n" sound. The vowel of the voice is collated with the voice, and when the voice recognized by the voice recognition device is the “n” sound, the function is provided to collate the “n” sound as it is.

An invention according to claim 11 is a communication system which enables communication by voice and image, and specifies a plurality of communication devices involved in communication from a transmission side communication terminal to a reception side communication terminal. Is characterized by being constituted by the communication system device according to any one of claims 1 to 10.

A twelfth aspect of the present invention is the communication system according to the eleventh aspect, wherein the specific communication device is a communication server that relays communication between the transmitting communication terminal and the receiving communication terminal. Features.

[0021]

Embodiments of the present invention will be described below with reference to the accompanying drawings. In the embodiment, a first embodiment (FIG. 1) in which a pseudo image is generated on the transmitting side, a second embodiment (FIG. 3) in which a pseudo image is generated on the receiving side, and an embodiment in which an intermediate server generates a pseudo image. Three configurations of the third embodiment (FIG. 5) will be described.

Embodiment 1 First, an embodiment for generating a pseudo image on the transmission side will be described with reference to FIG.
In the first embodiment, a communication terminal that generates a pseudo image is referred to as an image generation communication terminal 10 for the sake of convenience, whereas a conventional communication terminal that enables voice and image communication is a TV telephone (video telephone). ) 50. The image generation communication terminal 10 may be either a stationary type or a portable type. However, in the present embodiment, the image generating communication terminal 10 will be described as a portable type that exerts more advantageous effects of the present invention.

The TV phone 50 is provided with a speaker, a microphone, a monitor, and a camera to enable two-way voice and image communication.
The telephone 50 does not have a camera. That is,
The TV phone 50 includes a speaker 53, a microphone 54, and a monitor 5.
5 is provided.

As shown in the figure, the TV phone 50 includes a communication control device 51 and a control device 52.
0 is connected to the communication network 1 via the communication control device 51. Then, the communication control device 51 transmits and receives the audio signal and the image data to and from the communication destination terminal,
Audio and images are output from a speaker 53 and a monitor 55 connected to the control device 52, and the audio input from the microphone 54 is transmitted to the communication destination terminal via the communication control device 51. The connection form between the TV phone 50 and the communication network 1 is not limited to wired or wireless.

As shown in the figure, the image generation communication terminal 10 includes a speaker 16, a microphone 17, a monitor 18, and a camera 1.
9, but it is also possible to adopt a configuration without the camera 19 as described later. The speaker 16, the microphone 17, the monitor 18, and the camera 19 are connected to the control device 12, respectively, and communicate bidirectionally with a communication destination terminal via a communication control device 11 connected to the control device 12 by voice and image. Perform communication.

A voice recognition device 15 is interposed between the microphone 17 and the control device 12 to recognize voice from a voice signal received from the microphone 17. That is, the control device 12 inputs the voice signal of the voice input by the microphone 17 and the voice signal of the voice recognized by the voice recognition device 15.

The control device 12 is a mapping device 12
a and a pseudo image acquisition device 12b. The mapping device 12a includes a voice recognized by the voice recognition device 15;
This is a device that performs collation with a preset basic voice. The collation is a means for determining (mapping) a recognized voice to which basic voice is to be associated with, and a means for performing the association, and has a function of collating all the voices input by the microphone 17 with the basic voice. ing. In the following description, the description as the mapping process indicates the above-described collation process. Also, the pseudo image acquisition device 12b
Has a function of acquiring pseudo image data corresponding to audio mapped to basic audio.

The basic voice will be described later in detail, but here, as shown in FIG. 7, the basic voice for Japanese is "A", "I", "U", "E", "O", "N". , Ie, a group of voices composed of vowels and “n” sounds. When the voice is a voice other than the “n” sound, the mapping device 12a maps (collates) the vowel of the voice, and when the voice is the “n” sound, the mapping device 12a does not change the “n” sound. Is set to be mapped (matched). As a result, the voice input by the microphone 17 is all mapped to vowels and “n” sounds by the mapping device 12a.

[0029] For example, as shown in FIG. 8, when the voice of "Hello" is input by the microphone 17, the mapping unit 12a, "child" → "you,""I" → "I", "to" → " The mapping is performed in the order of "i""chi" → "i""ha" → "a".

The image generation communication terminal 10 has a pseudo image database 14. The pseudo image database 14 is a database that stores pseudo image data corresponding to the basic sound, and stores video information obtained by photographing the expression of the person who uttered the basic sound. In other words, as shown in FIG. 7, each vowel and “n” sound has pseudo image data of a facial expression of a person generating each sound.

As described above, all voices are mapped to basic voices by the mapping device 12a, and each of the basic voices corresponds to the corresponding pseudo image data in the pseudo image database 14.
, The pseudo image data can be associated with all the sounds.

In the above configuration, the image generation communication terminal 1
The operation state of 0 will be described. First, the above-described pseudo image database 14 is created as a previous step. The creation of the pseudo image database 14 is performed, for example, by photographing the expression of a person making a call using the image generation communication terminal 10 with the camera 19. Then, pseudo image data corresponding to each of the photographed vowels and “n” sounds is stored in the pseudo image database 14. The image generation communication terminal 10 is provided with an operation device 10a including operation keys and the like.
It is possible to make settings such as which basic sound the captured image corresponds to.

The pseudo image data can be taken by, for example, a digital camera, and the image data can be input from an external terminal 10b provided in the image generation communication terminal 10. With such a configuration, the image generation communication terminal 10 can be configured not to include a camera.

In the present embodiment, the mapping rule in the mapping device 12a is such that, for a sound other than the "n" sound, the vowel of the sound is made to correspond to the sound, and Is set to correspond to the “n” sound as it is. However, as described later, other mapping rules can be adopted, and a plurality of mapping rules can be held. If a plurality of mapping rules are held, the setting of the mapping rules may be changed using the operation device 10a.

In the state where the settings at the previous stage have been made, the user 2 of the image generation communication terminal 10 performs a dial operation with the operation device 10a to establish communication with the TV telephone 50 as the call destination. Alternatively, by the operation of the user 3 of the TV phone 50, a call is made from the TV phone 50 side, and the communication is established.
When the user 2 speaks to the microphone 17, the voice input to the microphone 17 is converted into a voice signal, voice recognition is performed in the voice recognition device 15, and the voice signal recognized together with the voice signal is output. It is sent to the control device 12. In the control device 12, the voice recognized by the mapping device 12a corresponds to the basic voice, and the pseudo image data is acquired from the pseudo image database 14 by the pseudo image generation device 12b. And the control device 12
Transfers the audio signal of the audio input from the microphone 17 and the pseudo image data obtained from the pseudo image database 14 to the communication control device 11. Then, the audio signal and the pseudo image data are transmitted to the TV phone 50 via the communication network 1 by the communication control device 11. FIG. 2 shows the flow of the audio signal and the pseudo image data described above.

When the communication control device 51 of the TV phone 50 receives the audio signal and the pseudo image data from the image generation communication terminal 10, the communication control device 51 transfers the signal to the control device 52, and the control device 52 extracts the audio signal and the image signal. Are output from the speaker 53 and the monitor 55, respectively.

As described above, the voice of the user 2 of the image generation communication terminal 10 and the pseudo image corresponding to the voice are output to the monitor 55 on the TV phone 50 side. Can be conducted in a state where is displayed on the monitor 55 in real time.

On the other hand, the audio signal input from the microphone 54 of the TV phone 50 is transmitted to the image generation communication terminal 10 via the communication control devices 51 and 11, and the image generation communication terminal 10
Is output from the speaker 16.

By adopting such a configuration, even when both use a communication terminal not equipped with a camera, it is possible to simulate a conversation while looking at the other party. For example, it is effective that the sales representative uses the image generation communication terminal 10 shown in FIG. By transmitting the pseudo image data when a customer makes an inquiry call, the sales representative can have his / her face remembered. In addition, the salesperson does not need to be prepared so that he can always take his picture with the camera.
Even when running around in work clothes, customers can be handled in the form of a pseudo image of wearing a suit and wearing a tie. Alternatively, a plurality of pseudo images may be registered in a database in a selectable manner in advance, and may be selected according to the situation.

In the case where the TV phone 50 is equipped with a camera, the user 2 of the image generating communication terminal 10 has a conversation while checking the appearance of the user 3 using the TV phone 50. It becomes possible.

Embodiment 2 Next, an embodiment for generating a pseudo image on the receiving side will be described with reference to FIG.
In the second embodiment, a communication terminal that creates a pseudo image is referred to as an image generation communication terminal 20 for the sake of convenience, whereas a conventional communication terminal that enables voice and image communication is a TV phone 50. Called. Note that the TV phone 50 has the same configuration as the terminal in the embodiment shown in FIG. 1, and the same numbers are assigned to the respective devices provided in the TV phone 50.

As shown in the figure, the image generation communication terminal 20 includes a speaker 26, a microphone 27, a monitor 28,
9, the camera 29 may not be provided as described in the first embodiment. The speaker 26, the microphone 27, the monitor 28, and the camera 29 are connected to the control device 22, respectively.
Via the communication control device 21 connected to the communication terminal 2, bidirectional communication by voice and image is performed with the communication destination terminal.

The control device 22 includes a speech recognition device 25.
Is connected, and the control device 22 recognizes a voice from a voice signal received from a communication partner. The control device 22 includes a mapping device 22a and a pseudo image acquisition device 22b, as in the first embodiment.
As for the basic voice, as in the first embodiment, “A”
It is composed of six voices “i”, “u”, “e”, “o”, and “n”, that is, a group of voices composed of vowels and “n” sounds. As a result, all the voices received by the control device 22 are made to correspond to vowels and “n” sounds by the mapping device 22a. Further, the image generation communication terminal 20 includes a pseudo image database 24.

As described above, the mapping device 22a maps (collates) all voices with basic voices, and each basic voice has corresponding pseudo image data in the pseudo image database 24. Can be associated with the pseudo image data.

The image generation communication terminal 20 in the above configuration
Will be described. First, as in the first embodiment, the pseudo image database 24 is created and mapping rules are set as in the first embodiment. Image generation communication terminal 2
0 includes an operation device 20a including operation keys and the like and an external terminal 20b as in the first embodiment.
It is possible to associate the video captured with the basic sound with the basic audio and change the setting of the mapping rule using the operation device 20a. Further, by inputting an image captured by a digital camera or the like from the external terminal 20b, it is possible to register pseudo image data generated externally in the pseudo image database 24.

In the state where the settings at the previous stage have been made, the user 4 of the image generation communication terminal 20 performs a dial operation with the operation device 20a to establish communication with the TV telephone 50 as a call destination. Alternatively, communication is established by a dial operation by the user 5 of the TV phone 50. When the user 4 speaks to the microphone 27, the voice input by the microphone 27 is converted into a voice signal, transmitted to the TV phone 50 via the communication control devices 21 and 51, and transmitted from the speaker 53 of the TV phone 50. Is output.

The image generation communication terminal 20 is connected to the camera 29
When the device is equipped, it is also possible to output audio and image data to the TV phone 50 by transmitting images and audio.

On the other hand, the voice uttered by the user 5 of the TV phone 50 is converted into a voice signal by the microphone 54 and transmitted to the image generation communication terminal 20 via the communication control devices 51 and 21. The voice signal transmitted to the image generation communication terminal 20 is passed to the control device 22, and the voice recognition device 25 performs voice recognition. Further, the control device 22 causes the recognized voice to correspond to the basic voice by the mapping device 22a, and obtains the corresponding pseudo image data from the pseudo image database 24 by the pseudo image acquisition device 22b. Then, the control device 22 transmits the audio signal received from the communication control device 21 to the speaker 26, and transmits the pseudo image data acquired from the pseudo image database 24 to the monitor 28. FIG. 4 shows the data flow of the audio signal and the pseudo image data described above.

In this way, the voice of the user 5 of the TV phone 50 and the pseudo image corresponding to the voice are output to the monitor 28 on the image generation communication terminal 20 side, so that the user 5 can talk. Is displayed on the user 4 side in real time.

By adopting such a configuration, even when both use a communication terminal not equipped with a camera, it is possible to have a conversation while looking at the other party in a pseudo manner. For example, the image generation communication terminal 20 is installed at home.
In this case, the image generation communication device 20 may be a stationary type. Then, it is assumed that the father who works for the company has a mobile phone (corresponding to the TV phone 50 shown in FIG. 3, but in this case, a general mobile phone having no TV phone function may be used). Then, if the father who leaves the office and goes home returns and calls home with a mobile phone and has a conversation such as "I'm going home soon," the image generation communication terminal 20 at home stores the image in the pseudo image database 24 in advance. By using the father's pseudo image data, it is possible to display a video as if the father is having a conversation. If this is used, a small child who is returning home from his father can have a conversation while watching the image of his father.

There is also an advantage that the communication terminal carried by the father can use a normal mobile phone. That is, in the embodiment shown in FIG. 3, the terminal used by the user 5 is described as the TV phone 50. However, in the present embodiment, the terminal used by the user 5 is a telephone ( Mobile phone).

Also, in the configuration shown in FIG.
Data transmitted from 0 to the image generation communication terminal 20 is only an audio signal. Thereby, there is also an advantage that the load on the communication network 1 can be reduced.

Third Embodiment Next, the configuration of a third embodiment in which a pseudo image is created by an intermediate server will be described with reference to FIG. In the third embodiment, conventional communication terminals that enable communication by voice and image are referred to as TV phones 50A and 50B, but the TV phones 50A and 50B are the same as the TV phones 50 shown in FIG. Configuration.

The communication server 30 includes a communication control device 31 having a reception control device 36 and a transmission control device 37, a control device 32, a mapping device 32a, and a pseudo image acquisition device 32.
b, a pseudo image database 34, a voice recognition device 35, and the like. The control device 32 and the mapping device 32
a, pseudo image acquisition device 32b, pseudo image database 3
4. The configuration and functions of the voice recognition device 35 are shown in FIGS.
The configurations and functions of the devices corresponding to the image generation communication terminals 10 and 20 shown in FIG.

Similarly, for the basic voices, the basic voices are divided into six voices “A”, “I”, “U”, “E”, “O”, and “N”.
In other words, it is composed of a group of voices composed of vowels and “n” sounds. Thereby, the voice received by the communication server 30 is
By the mapping device 32a, all the vowels and "n" sounds are mapped.

As described above, all voices are mapped to basic voices by the mapping device 32a, and each of the basic voices corresponds to the corresponding pseudo image data in the pseudo image database 34.
, The pseudo image data can be associated with all the sounds.

The operation state of the communication server 30 in the above configuration will be described. First, as in the first embodiment, as in the first and second embodiments, the creation of the pseudo image database 34 and the setting of mapping rules are performed.

In the state where the setting of the previous stage has been made, the TV
The user 6 of the telephone 50A establishes communication with the TV telephone 50B, which is the call destination, by performing a dial operation. Alternatively, communication is established by a dial operation of the user 7 of the TV phone 50B. Then, the user 6 uses the microphone 5
When speaking to 4A, the voice input by microphone 54A is converted to a voice signal and transmitted from communication control device 51A. Then, the audio signal is transmitted to the communication server 30 instead of being directly transmitted to the TV phone 50B side.

The audio signal transmitted to the communication server 30 is
It is passed to the control device 32 via the reception control device 36. The voice signal input by the control device 32 is subjected to voice recognition in the voice recognition device 35, and the recognized voice signal is returned to the control device 32. Then, the control device 32 causes the recognized voice signal to correspond to the basic voice by the mapping device 32a. Further, the pseudo image data of the corresponding basic sound is obtained from the pseudo image database 34 by the pseudo image obtaining device 32b.

As described above, the communication server 30 acquires the pseudo image data based on the audio signal received from the TV telephone terminal 50A, and transmits the acquired pseudo image data together with the received audio signal from the transmission control device 37 to the TV telephone 50B. It is sent to the side.

The TV telephone 50B receives the audio signal and the pseudo image data from the communication server 30 in the communication control device 51B, and transfers it to the control device 52B. Then, the audio signal extracted by the control device 52B is output from the speaker 53B, and the image data is output to the monitor 55B.

On the contrary, the microphone 5 of the TV phone 50B
The voice input in 4B is voice-recognized and mapped in the communication server 30, and transmitted to the TV phone 50A together with the pseudo image data.

Thus, the TV phone 50B side
The voice of the user 6 of the TV phone 50A is reproduced by the speaker 53B, a pseudo image corresponding to the voice is output to the monitor 55B, and the voice of the user 7 of the TV phone 50B is displayed on the TV phone 50A side. 53A, and a pseudo image corresponding to the sound is displayed on the monitor 55A.
Is output to the user, so that both users can talk as if they are watching the video of the other party in conversation.

In this embodiment, the pseudo image database 34 of the communication server 30 holds the pseudo image data of both the user 6 and the user 7, and the user 6 The pseudo image data transmitted together with the audio signal to the user 7 is a pseudo image in which the user 6 utters the basic voice, and the pseudo image data transmitted together with the audio signal from the user 7 to the user 6 is the user. Reference numeral 7 denotes a pseudo image producing a basic sound.

By adopting such a configuration, even when both use a communication terminal not equipped with a camera, it is possible to have a conversation while simulating the appearance of the other party. According to the present embodiment, the terminal used by each user does not need to be provided with a voice recognition device or a pseudo image database, so that the cost of the entire system can be reduced.

{Basic Voice and Mapping Apparatus} In each of the above-described embodiments, the basic voice is “A”.
An example has been described in which five vowels “I”, “U”, “E”, and “O” and “N” sound are used, but the basic voice is not limited to this. In the case where the expression of the person who utters the voice of the above is classified into several patterns, it may be constituted by the voice representing the pattern.

To explain an example in which a basic voice is composed of vowels and "n" sounds, the expression of a person who utters the voice, that is, the shape of the mouth is similar to the expression of the person who utters the vowel of the voice. That is the nature of that. That is,
According to the expression of the person who utters the vowel, the expression of the person who utters the voice can be classified into five patterns. However, since the facial expression with the mouth closed does not exist in the five vowels, all facial expressions emitting voice are covered by vowels and "n" sounds by adding the "n" sound to the basic voice. They are trying to do it.

Similarly, for example, the facial expression of the person who uttered the voice is classified according to its characteristics, and the "voice uttered with the mouth closed" or the "voice uttered with the mouth closed slightly" If the voices belonging to the same pattern are mapped (matched) to the basic voice and a pseudo image of the basic voice is used, Good.

As described above, if the method is to classify voices into patterns belonging to the basic voices and use a pseudo image of the basic voices, there is no effect even if the language generated by the user is not Japanese. . That is, when the input voice is, for example, English, the English pronunciation may be classified by a pattern including the basic voice, and all voices may be mapped to the basic voice. In addition, even if the input voice is in English, if a certain degree of accuracy is tolerated, by performing voice recognition in Japanese, the above-described mapping method in which the vowel and the "n" sound are used as the basic voice is used. It can be used as it is.

{Pseudo Image Data} In the above-described embodiment, the pseudo image data is, as shown in FIG.
The video information includes the facial expression of the person uttering the basic sound. On the other hand, since the facial expression of the person who is uttering the voice has the most characteristic at the lip, the pseudo image data may be video information of only the lip. In this case, as shown in FIG. 9, parts other than the mouth, that is, other parts of the face such as eyes and nose, and a background part behind a person are different video information (common image data) as common parts. Make it easier,
The video of the common portion and the video information (mouth image data) of the mouth portion may be combined.

When the pseudo image data is configured as described above, the capacity of the image data of the fluctuating portion (mouth portion) can be reduced, so that the capacity of the pseudo image database can be reduced. Further, the characteristic portion such as the lip and the eye and the lip and the eyebrows may be a combination of a plurality of image data.

<< Application Example >> A communication terminal or the like using a pseudo image described above can perform pseudo-TV communication even if both parties performing communication (call) do not own a TV phone equipped with a camera.
Although the effect of maintaining the function as a telephone can be obtained, various applications as described below are possible regardless of the presence or absence of a camera.

(1) Answering Machine Mode When the telephone cannot be answered, such as during a meeting or in a train, the mobile phone may be in the answering machine recording mode. When the call arrives, an answering machine message recorded in advance or held in advance by the mobile phone is played. Then, by mapping the voice of the answering machine message to the basic voice and acquiring the pseudo image data, it is possible to transmit the pseudo image data together with the answering machine message to the other party. Thereby, it is possible to transmit an answering machine message as if the person is talking.

Also, if the other party who calls the telephone while in the answering machine recording mode leaves a message, but has pseudo image data of the other party, it is as if the person is talking. Message can be checked later.

(2) Agent Mode In the above-described embodiment, the pseudo image data is a facial expression of a person who emits a voice. By transmitting the pseudo image data of a person who is actually talking, the pseudo image data is transmitted. The pseudo image is effective, but the pseudo image may be replaced with an image of a completely different person or an image of an animated character or the like.

For example, when it is absolutely necessary to convey difficult-to-talk content to the other party, it is possible to use a method of having a conversation using an animation character image instead. In addition, it is also possible to use such a method that a woman suffering from a harassment telephone call uses a pseudo image of a strong man to take measures against repulsion instead. Such an agent character may be obtained, for example, by downloading data provided on the Internet or the like.

(3) Background Mode For the pseudo image data, it is only necessary to prepare one image corresponding to each of the basic sounds, but a plurality of types of pseudo image data for one basic sound is stored in the pseudo image database. You may make it accumulate. In other words, a plurality of types of pseudo image data having different backgrounds are stored for the sound "a" as the basic sound.

For example, if pseudo image data corresponding to the basic sound taken in the company is transmitted to the called party as pseudo image data for “in-house”, even if the user is outside the company, it is as if a call is made from within the company. The effect as described above is obtained.
Also, if you shoot an image corresponding to the basic sound at any of the sightseeing spots as pseudo image data for "sightseeing", you can call from the sightseeing spot even if you return from the sightseeing spot The same effect can be obtained.

By using a plurality of types of pseudo image data having different backgrounds as described above, it is possible to use the pseudo image data according to various uses. In the background mode, for example, in the embodiment shown in FIG. 1, a plurality of types of pseudo image data such as “for office” and “for sightseeing” are stored in the pseudo image database 14 and the operation device At 10a, the switching operation of the background mode may be enabled. As a result, the pseudo image acquisition device 12b acquires the mapped basic sound and the pseudo image data corresponding to the background mode, and the pseudo image corresponding to the background mode is transmitted to the communication destination.

[0080]

As described above, according to the first aspect of the present invention, the communication terminal on the transmitting side performs the speech recognition, generates the pseudo image data, and transmits the voice and the pseudo image to the communication destination. With this configuration, even if the transmitting side is a terminal not equipped with a camera, the same effect as a videophone can be obtained in a pseudo manner.

According to the second aspect of the present invention, the communication terminal on the receiving side is configured to perform voice recognition of the received voice, generate pseudo image data, and output the voice to the speaker and the pseudo image data to the monitor. Therefore, even if the transmitting side is a terminal without a camera, the same effect as a videophone can be obtained. Further, since only the audio signal is transmitted to the communication network, the load on the line can be reduced.

According to the third or twelfth aspect of the present invention, the intermediate communication server performs voice recognition of the voice transmitted from the transmitting side communication terminal, generates pseudo image data, and transmits the voice and the pseudo image data to the receiving side. Since the transmission is performed to the communication terminal, even if the transmission side is a terminal not equipped with a camera, the same effect as a videophone can be obtained in a pseudo manner. Furthermore, since only the communication server needs to include the voice recognition device and the pseudo image database, the cost of the entire system can be reduced.

According to the fourth aspect of the present invention, the pseudo image data is
Since the video information includes the expression of the person who utters the basic voice, the other party who is looking at the pseudo image data can feel as if he or she is talking.

According to the fifth aspect of the present invention, the pseudo image data is
Since the video information represents the shape of the mouth of the person who utters the basic sound, the other party who is looking at the pseudo image data can feel as if the person is talking.
Further, by reducing the capacity of the image data of the fluctuating portion, it is possible to save the capacity of the pseudo image database.

According to the sixth aspect of the present invention, the pseudo image database includes a plurality of types of pseudo image data having different backgrounds for one basic voice. It is possible to obtain the effect of making a call.

According to the seventh or eighth aspect of the present invention, since the basic voice includes five vowels, it is possible to classify the facial expression of the person who utters the voice with the minimum basic voice.

According to the ninth or tenth aspect of the present invention, since the basic voice includes five vowels and the "n" sound, the facial expression of a person who emits the voice can be classified with the minimum basic voice, and the basic voice can be covered. Classification is possible.

According to the eleventh aspect of the present invention, by using the communication system apparatus according to any one of the first to tenth aspects, it is possible to configure various systems using a pseudo image, and the above-described effects are obtained. Can be

[Brief description of the drawings]

FIG. 1 is a configuration diagram of a terminal and a system according to an embodiment for creating pseudo image data in a transmission terminal.

FIG. 2 is a diagram showing a data flow in the embodiment shown in FIG.

FIG. 3 is a diagram showing a terminal and system configuration of an embodiment for generating pseudo image data in a receiving terminal.

FIG. 4 is a diagram showing a data flow in the embodiment shown in FIG.

FIG. 5 is a diagram showing a terminal and system configuration of an embodiment for creating pseudo image data in an intermediate server.

FIG. 6 is a diagram showing a data flow in the embodiment shown in FIG.

FIG. 7 is a diagram showing a correspondence between a basic sound and a pseudo image.

FIG. 8 is a diagram illustrating an outline of processing of a mapping device.

FIG. 9 is a diagram showing a configuration of pseudo image data using a lip image.

[Explanation of symbols]

 Reference Signs List 10 image generation communication terminal 11 communication control device 12 control device 12a mapping device 12b pseudo image acquisition device 14 pseudo image database 15 voice recognition device 16 speaker 17 microphone 18 monitor 19 camera 50 TV phone 51 communication control device 52 control device 53 speaker 54 microphone 55 monitors

──────────────────────────────────────────────────の Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) H04N 5/76 G10L 5/06 D (72) Inventor Minoru Kuwana 2-3 Azuchicho, Chuo-ku, Osaka-shi, Osaka No. 13 Osaka International Building Minolta Co., Ltd. (72) Inventor Tsutomu Honda 2-3-3 Azuchicho, Chuo-ku, Osaka City, Osaka Prefecture Osaka International Building Minolta Co., Ltd. (72) Inventor Kazuhiko Ishimaru Chuo, Osaka City, Osaka Osaka International Building Minolta Co., Ltd. 2-3-1-13 Azuchi-cho, Ward (72) Inventor Hideki Nagata 2-3-13 Azuchi-cho, Chuo-ku, Osaka-shi, Osaka F-term in Osaka International Building Minolta Co., Ltd. 5C052 AA12 AB04 AC02 DD02 DD06 EE03 5D015 AA01 BB02 CC18 KK02 5K101 KK04 LL12 MM07 NN07 NN08 NN16 NN18 NN23 NN36 NN37

Claims (12)

[Claims] An apparatus for a communication system enabling communication by voice and image, wherein the apparatus for a communication system is configured as a communication terminal, wherein the communication terminal includes: a microphone for inputting sound; A voice recognition device that receives a voice signal from the voice recognition device and performs voice recognition; a mapping device that performs matching between the voice recognized by the voice recognition device and a predetermined basic voice; and corresponds to the predetermined basic voice. A pseudo image database that accumulates the obtained pseudo image data, a pseudo image acquisition device that obtains pseudo image data corresponding to the collated basic sound from the pseudo image database, an audio signal of an audio input from the microphone, A communication control device for transmitting the pseudo image data acquired by the pseudo image acquisition device to the designated communication destination terminal. Communication system, characterized in Rukoto device. 2. An apparatus for a communication system that enables communication by voice and image, wherein the apparatus for a communication system is configured as a communication terminal, and the communication terminal transmits an audio signal transmitted from a communication destination terminal. A voice recognition device that recognizes a voice from a voice signal received by the communication control device; and performs collation between a voice recognized by the voice recognition device and a predetermined basic voice. A mapping device, a pseudo image database storing pseudo image data corresponding to the predetermined basic sound, and a pseudo image obtaining device obtaining pseudo image data corresponding to the collated basic sound from the pseudo image database. A speaker that reproduces an audio signal received by the communication control device as audio; And a monitor for outputting similar image data. 3. An apparatus for a communication system which enables communication by voice and image, wherein said apparatus for a communication system is configured as a communication server, and said communication server transmits a voice transmitted from a communication terminal on the transmitting side. A reception control device that receives a signal, a speech recognition device that performs speech recognition from a speech signal received by the reception control device, and a comparison between a speech recognized by the speech recognition device and a predetermined basic speech. A pseudo-image database that stores pseudo-image data corresponding to the predetermined basic sound; and a pseudo-image acquisition device that obtains pseudo image data corresponding to the collated basic sound from the pseudo image database. Transmitting the audio signal received by the reception control device and the pseudo image data acquired by the pseudo image acquisition device Communication system, characterized in that it comprises a transmission control unit that transmits to the communication terminal apparatus. 4. The communication system device according to claim 1, wherein the pseudo image data is video information including a facial expression of a person who utters the basic sound. Communication system device. 5. The communication system device according to claim 1, wherein the pseudo image data is video information representing a shape of a mouth of a person who utters the basic sound. An apparatus for a communication system, comprising: 6. The communication system device according to claim 4, wherein the pseudo image database includes a plurality of types of pseudo image data having different backgrounds for the same basic sound. An apparatus for a communication system, comprising: 7. The communication system device according to claim 4, wherein the basic voice includes a combination of five vowels for a predetermined language, and the pseudo image database includes: An apparatus for a communication system, comprising at least pseudo image data corresponding to each of the vowels. 8. The communication system device according to claim 7, wherein the mapping device includes a function of comparing a vowel of the voice with a voice recognized by the voice recognition device. System equipment. 9. The communication system device according to claim 4, wherein the basic voice includes five vowels and “n” sound for Japanese, and the pseudo image database. Comprises at least pseudo image data corresponding to each of the vowels and the "n" sound. 10. The communication system device using the pseudo image according to claim 9, wherein the mapping device is configured to, when the voice recognized by the voice recognition device is a voice other than the “n” sound. An apparatus for a communication system, comprising a function of collating a vowel of the voice with the voice and, when the voice recognized by the voice recognition device is a "n" sound, collating the "n" sound as it is. 11. A communication system capable of voice and image communication, wherein a specific communication device among a plurality of communication devices involved in communication from a transmitting communication terminal to a receiving communication terminal is: A communication system comprising the communication system device according to any one of claims 1 to 10. 12. The communication system according to claim 11, wherein the specific communication device is a communication server that relays communication between the transmitting communication terminal and the receiving communication terminal. Communications system.