JPH0713582A - Portable speech recognition output assisting device - Google Patents

Abstract

PURPOSE:To correctly recognize an inarticulate voice that a handicapped person speaks and to output a speech signal including the sensation of the voicing person. CONSTITUTION:This portable speech recognition output assisting device is provided with a speech input/output device 1 which has a speech input means 12 and a speech output means 13, a speech recognition part 2 which recognizes a voice print, an intonation, a pitch, and a generated sound from a vibration frequency signal inputted to the speech input means 12, a speech code decision part 3 which stores plural standard speech patterns and speech codes corresponding to the patterns. compares a speech code regarding the recognized generated sound with the stored speech codes, and outputs speech information on the voice print, intonation, pitch, etc., in addition to the standard speech pattern corresponding to the speech code when both the speech codes match each other, a speech synthesis part 5 which puts the standard speech pattern and voice print together and adds the intonation of the sound to synthesize a sound, and a speech conversion output part 7 which outputs the synthesized sound to a speech signal from the speech output means 13.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a portable voice recognition output assisting device suitable for use by a person who utters an unclear voice such as a vocal cord extractor or a physically handicapped person. The present invention relates to a portable voice recognition output assisting device capable of appropriately recognizing an unclear voice and assisting in conversation.

[0002]

2. Description of the Related Art A conventional voice recognition apparatus stores in advance a large number of standard voice patterns corresponding to a voice uttered by a healthy person, and a voice pattern uttered by the mouth of the normal person and a large number of standard voices stored in advance. A pattern is compared and collated, and if there is a standard voice pattern that matches the voice pattern uttered by a healthy person, the voice uttered by a healthy person is recognized from the standard voice pattern.

On the other hand, a voice synthesizer is a device for outputting a voice, in which a voice uttered by an announcer is recorded, compressed and recorded into low bits by an analysis method, and then reproduced when it is output. , There is a rule synthesizing method in which a single tone is combined in correspondence with an input kana and an accent and an intonation are superimposed. The former is used as the output of the voice response device and is used in the order entry field in combination with the PB input of a touch-tone phone. The latter has been developed with a technology for directly converting Japanese and English sentences into speech, and there are great expectations for the future development of the technology.

[0004]

However, the conventional voice recognition device performs voice recognition from a voice pattern uttered by a healthy person's mouth. It cannot recognize the voices emitted by those who have lost the voices or the unhealthy persons who make unclear voices. The reason for this is that not only is unrecognizable due to the unclear voice being uttered, but also air vibration of the voice uttered from the mouth is detected, so the person who extracted the vocal cords and the tongue cancer lost the tongue. In the case of a person, it is not applicable because it does not utter a voice originally.

Depending on the future technological progress, an unspecified number of voice recognitions will be possible, and various devices using the voice recognition device will be used in daily life. In any case, it is considered to be the development of a device effective for the healthy person. Therefore, it seems that it is very difficult for an unhealthy person with various disabilities to use it sufficiently even if a new device is developed because the voice is unclear or the voice generation speed is slow. Be done.

On the other hand, in the case of the speech synthesizer, it does not produce many words or emotional speech signals uttered by an individual, which is still insufficient from the viewpoint of conversation.

The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a portable voice recognition output assisting device capable of surely inputting a signal corresponding to a voice even by a person who cannot speak the voice. .

Another object of the present invention is to provide a portable voice recognition output assisting device which correctly recognizes an unclear voice uttered by an unhealthy person and realizes voice synthesis including the emotion of the person who utters the voice. To provide.

Still another object of the present invention is to provide a portable voice recognition output assisting device for generating an appropriate voice signal while considering the physical condition of an unhealthy person. Furthermore, another object of the present invention is that an unhealthy person can easily wear it,
Another object of the present invention is to provide a portable voice recognition output assisting device with excellent operability.

[0010]

In order to solve the above-mentioned problems, the invention according to claim 1 is directed to the back side of a strip-shaped mounting body formed of a sound absorbing cloth which is wound around and fixed to a vibration generator. Is attached with a flat voice input means for detecting the vibration generated from the vibration generator and converting it into an electric vibration frequency signal, and further outputs a voice signal corresponding to the vibration frequency signal on the surface side of the mounting body. It is a portable voice recognition output assisting device having a voice input / output device to which a flat voice output means is attached.

Next, the invention according to claim 2 is a voice input means for detecting a vibration generated from a vibration generator and outputting an electric vibration frequency signal, and a vibration frequency signal inputted by the voice input means. A voice input / output device having a voice output means for outputting a voice signal according to the above, and a voice recognition part for recognizing a voiceprint, a sound intensity, a pitch, and a generated sound from a vibration frequency signal input from the voice input means, A plurality of standard voice patterns and voice codes corresponding to the patterns are stored in advance, the voice code relating to the generated sound recognized by the voice recognition unit is compared with the already stored voice code, and both voice codes are When they match, the standard voice pattern corresponding to the voice code is read, and the voice information including the standard voice pattern, the voiceprint, the strength of the sound, the pitch, etc. is read. A portable voice recognition output assisting apparatus provided with a speech code decision unit for force.

Next, in the invention corresponding to claim 3, in addition to the constituent features of the invention according to claim 2, the standard voice pattern newly output from the voice code determination section and the voiceprint are synthesized, Further, a voice synthesizing unit that creates a synthetic voice by adding the strength and the pitch of the sound, and a voice conversion output unit that converts the synthetic voice created by the voice synthesizing unit into a voice signal and outputs the voice signal from the voice output means. Is a portable voice recognition output assisting device.

Further, in the invention according to claim 4, in addition to the constituent features of the invention according to claim 2, the standard voice pattern and the voiceprint newly output from the voice code determination section are synthesized, and A voice synthesizing unit that creates a synthetic sound by adding the strength and the pitch of the sound, a voice storing unit that stores the synthetic voice created by the voice synthesizing unit, and a voice that outputs the synthetic voice stored in the voice storing unit. From the voice conversion output unit, a voice conversion output unit that converts the signal to output from the voice output unit, a voice repeat switch that reads the synthetic sound stored in the voice storage unit and repeatedly outputs the voice from the voice output unit, A voice speed changing means for changing the speed of the output voice signal, and a voice strength changing means for changing the voice signal level output from the voice conversion output section to add strength to the voice signal are added. It is a speech recognition output auxiliary equipment for the band.

Further, the invention according to claim 5 is a voice input / output device portion having voice input means and voice output means, and a main body device portion having a voice recognition portion, a voice code determination portion, and a voice conversion output portion. A voice repeat switch for reading the synthetic sound stored in the voice storage unit and repeatedly outputting it from the voice output unit, a voice speed changing unit for changing the speed of a voice signal output from the voice conversion output unit,
The portable voice recognition output assisting device is divided into a voice adjusting portion having a voice intensity varying means for varying the voice signal level output from the voice converting and outputting part to give a dynamic intensity.

[0015]

Therefore, the invention according to claim 1 uses the above-mentioned means, and by using the sound absorbing cloth for the vibration generator, for example, the wearing body which is fixed by being wound around the neck of an unhealthy person, and By installing flat voice input means and voice output means separately on the back side and front side of the wearing body, it is possible to prevent the influence of the voice uttered from the mouth and the noise coming from the outside, and it is unhealthy. The burden on the person's throat is reduced, and the vibration directly emitted from the throat can be reliably input.

Next, in the invention according to claim 2, the voice recognition unit recognizes the voiceprint, the strength of the sound, the pitch of the sound, and the vocal sound from the vibration frequency signal input from the voice input means, and the voice code determination unit. Send to. In this voice code determination unit, since a plurality of standard voice patterns and voice codes corresponding to the patterns are stored in advance, the voice code relating to the generated sound sent from the voice recognition unit and the voice code already stored. When both voice codes match, the standard voice pattern corresponding to the voice code is read out, and voice information including the standard voice pattern, the voiceprint, the strength of the sound, and the pitch is output. An unclear voice uttered by a person can be correctly recognized, and a standard voice pattern converted from a short word uttered by an unhealthy person into a long word used for daily conversation can be easily output.

Further, the invention according to claim 3 has the same operation as that of the invention according to claim 2, and the standard voice pattern and the voiceprint sent from the voice code determination part in the voice synthesis part. Is synthesized, and the synthesized voice is created by adding the strength and weakness of the sound, so that you can synthesize the voice including emotions.
Moreover, since the synthesized signal is converted into a speech signal in the speech signal conversion output section and is outputted from the speech output means, a speech signal accompanied by emotional expression can be outputted.

Furthermore, the invention according to claim 4 has the same operation as the invention according to claims 2 and 3, and also operates the voice repeat switch to read the synthesized voice again from the voice storage unit. Since it is repeatedly output from the voice output means, the same voice signal can be output without producing a voice from the beginning even when the partner hears it again. Further, by changing the output speed of the audio signal by the audio speed changing means, it is possible to output the audio signal at a speed that is easy for a healthy person to understand. Further, since the voice signal level is varied by the voice intensity varying means and the voice signal is given with the varying strength, the voice signal can be output similarly to a normal person.

Further, the invention according to claim 5 is a main body device having a voice input / output device portion having voice input means and voice output means, a voice recognition portion, a voice code determination portion, a voice signal conversion output portion and the like. By dividing into a part and a voice adjustment part having various adjustment functions, the voice input / output device part is wrapped around the neck of an unhealthy person, the main body device part is hung on the waist part of the body, etc. If you carry it by hand, you can carry it easily and operate it easily.

[0020]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing the configuration of the device of the present invention. In the figure, reference numeral 1 is a voice input / output device, and as shown in FIG. 2, this is a wearing body 1 of, for example, a cloth such as a corset that is wrapped around the neck in the case of whiplash.
1 is used, and an audio input means 12 for directly taking in vibrations uttered from the throat and an audio output means 13 for outputting an audio signal are attached to an appropriate portion of the wearing body 11, and are further attached to be wound around the neck and fixed. Velcro tapes 14a and 14b are attached to the facing surfaces of both ends of the body. It should be noted that various other well-known fixing means such as hooks other than the magic tapes 14a and 14b may be used for fixing.

The mounting body 11 is made of, for example, a cloth having a good sound absorbing property such as a curtain cloth for blocking external noise,
This absorbs the voice uttered by the mouth and the noise coming from the outside, and does not affect the voice input means 12. The voice input unit 12 is flatly attached to the back (inner) surface of the wearing body 11, and converts the vibration uttered from the throat into an electric signal and outputs the electric signal. By flattening in this way, it is easy to fit the wearing body 11, does not have a feeling of pressure on the throat, and can reduce the burden on the throat. On the other hand, in the voice output means 13, a flat speaker is similarly attached to the side opposite to the voice input means 12, that is, on the front (outer) surface of the mounting body 11. By mounting the flat speaker on the front in the same vertical line as the mouth in this way, the burden on the throat is reduced, and a state in which voice is emitted from the mouth when viewed from the other party is created. In addition, the sound output means 13 is mounted in a natural mounting state that is inconspicuous as long as it is out, by covering it with a color similar to that of the mounting body 11 or by using an appropriate material, or by taking appropriate measures for the color of the sound output means 13. To do.

Reference numeral 2 is a voice recognition unit for recognizing the characteristics of the personal voiceprint, the strength and weakness of the sound, and the correct utterance from the voice vibration frequency signal input from the voice input means 12. As shown in FIG. 3, the voice recognition unit 2 includes a voice spectrum conversion unit 21, a sound quality determination unit 22, a voiceprint determination unit 23, a vocal sound recognition unit 24, and the like. The voice spectrum conversion means 21 converts the voice vibration frequency signal as shown in FIG. 4 (a) into a voice spectrum as shown in FIG. 4 (b) by sampling the voice vibration frequency signal at a predetermined cycle. The sound quality judging means 22 judges the strength and the height of the sound from the voice spectrum, and the strength of the sound is
A predetermined reference level is set in advance, and it indicates how far each component of the voice spectrum is vertically separated from the reference level. On the other hand, the pitch of the sound depends on the frequency of the sound. Represents exclusively the level of each component of the speech spectrum. The voiceprint determination means 23 extracts the frequency component level of the voice spectrum, and the voicing sound recognition means 24 determines the voicing sound from the distribution state of the voice spectrum, and the character code corresponding to the voicing sound, for example, "A". It is converted into a code such as "a" or "a" and output. Then, the data judged by these judging means 22 to 24 are outputted in time series and sent to the voice code judging section 3.

The voice code determination section 3 stores a standard voice pattern and a voice code corresponding thereto in advance, and extracts a character code (voice code) which is a correct vocal sound recognized by the vocal recognition unit 24. , And has a function of comparing this voice code with a voice code already stored and, when both voice codes are the same, outputting a standard voice pattern corresponding thereto. Specifically, as shown in FIG. 5, a voice pattern storage unit 31 for storing a standard voice pattern,
A voice code storage means 32 for storing a voice code corresponding to each standard voice pattern of the voice pattern storage means 31;
It is constituted by the voice code judging means 33.

The voice code judging means 33 puts the data concerning the strength and weakness of the sound from the sound quality judging means 22 and the voiceprint feature data from the voiceprint judging means 23 into a buffer memory waiting state, and is recognized by the vocal sound recognizing means 24. For the voice code of the generated correct uttered sound, the voice code and a large number of voice codes stored in the voice code storage unit 32 are compared and referred to. The standard voice pattern corresponding to the voice code is extracted from the storage means 31 and stored in the voice information storage unit 4 together with the data already in the buffer memory waiting state. At this time, the voice code of the generated sound of the generated sound recognition means 24 may be stored at the same time. On the other hand, the uttered sound recognition means 24
When the voice code recognized by the voice code and the voice code already stored do not match, the uttered sound recognition means 24
The voice code of the uttered sound recognized in is output.

The standard voice patterns stored in the voice pattern storage means 31 are patterns corresponding to words used in daily conversation such as "Good morning", "Thank you", and "Goodbye". is there. That is, by converting the short speech code into the long words, the unhealthy person is sufficiently patterned to speak without uttering all the words.

The voice information storage unit 4 temporarily stores voice information such as the characteristics of the voiceprint, the strength and weakness of the sound, the pitch of the sound and the standard voice pattern related to the uttered sound, and the voice code of the recognized generated sound as necessary. After that, the speech is sent to the voice synthesizer 5.

In the voice synthesizing section 5, as shown in FIG. 6, the voice information storing means 51 for storing the voice information sent from the voice information storing section 4 and the voice information storing means 51 are stored. Of the voice information, the standard voice pattern and the voiceprint feature data are combined, and the strength and weakness of the sound and the pitch of the sound are added to the synthesized sound to create a completely demodulated synthesized sound, and the succeeding voice storage unit 6 and a voice synthesizing means 52 to be stored.

Reference numeral 7 denotes a voice conversion output unit, which has a function of reading the synthesized voice information stored in the voice storage unit 6, converting it into an analog signal capable of voice output, and outputting voice from the voice output means 13. I have

Further, this apparatus is provided with a voice output adjusting section 8. The reason for providing this audio output adjustment unit 8 is
The purpose is to be able to appropriately convey the content of the conversation to the other side according to the situation of an unhealthy person. That is, when the voice signal output from the voice output unit 13 is heard again by the other party, the voice output adjusting unit 8 performs a read operation to repeatedly output a synthesized voice from the voice storage unit 6. A repeat switch 81 is provided. this is,
This is because it is very difficult for an unhealthy person to make the same voice from the beginning, so that the burden is reduced.

Further, the voice output adjusting section 8 is provided with a voice speed varying device 82 and a voice intensity varying device 83. An analog first-order delay circuit using a capacitor or the like is incorporated in advance on the voice conversion output unit 7 side, and the speed of the voice signal is changed by appropriately short-circuiting the first-order delay circuit with the voice speed changer 82. . This is because the utterance speed of the non-healthy person is not necessarily high, and therefore the output speed of the synthetic sound output from the voice output means 13 is appropriately changed so that the sound person can hear easily. Further, the voice strength varying device 83 outputs the voice signal with strength and weakness by varying the level of the voice signal on the side of the voice conversion output unit 7 or varying the amplification factor. This is to make the voice signal output from the voice output means 13 strong and weak so that it can be heard easily even in the presence of a lot of external noise.

Next, the operation of the apparatus configured as described above will be described. First, a non-healthy person uses the voice input / output device 1
After the mounting body 11 is wrapped around the neck, the velcro tape portions provided on the opposite surfaces of the mounting body 11 are pressed and fixed. At this time, the voice output means 13 attached to the wearing body 11 is set so as to come to the front position, and the voice input means 12 is set at a position where the vibration of the throat is most easily taken in, for example, the side portion of the neck. . At this time, the voice input means 1
2 and the output means 13 are formed in a flat shape,
It easily fits on the neck and reduces the strain on the throat.

When an unhealthy person produces a voice in this state, the vibration of the throat of the unhealthy person is captured by the voice input means 12, converted into an electric vibration frequency signal, and sent to the voice recognition section 2.

Here, the voice recognizing unit 2 includes the voice inputting means 1
After the vibration frequency signal input from 2 is converted into the voice spectrum by the voice spectrum conversion means 21, the sound quality determination means 22, the voiceprint determination means 23, and the generated sound determination means 24.
Send to. Each of the judging means 22 to 24 determines the strength and weakness of the sound, the pitch of the sound, the characteristics of the voiceprint and the correct generated sound according to the above-mentioned judgment conditions, and in the case of the generated sound, a character code (voice code) corresponding to the generated sound To the voice code determination unit 3 together with the strength of the sound, the pitch of the sound, and the feature data of the voiceprint.

In the code judging section 3, a standard voice pattern is stored in advance in the voice pattern storage means 31, and a voice code corresponding to the standard voice pattern is stored in the voice code storage means 32. Particularly, the standard voice pattern is stored. The patterns are stored in the form of patterns corresponding to words used in daily conversation such as “Good morning”, “Thank you”, and “Goodbye”.

Therefore, in the code determination section 3, the speech recognition section 2
When a character code (speech code) that is the correct uttered sound recognized by is received, some of the speech codes are compared with the already stored speech codes, and when both speech codes are the same, corresponding The standard voice pattern to be read is read out and sent to the voice synthesizing section 5 via the voice information storage section 4 together with the data regarding the strength and weakness of the sound from the sound quality determining means 22 and the voiceprint characteristic data from the voiceprint determining means 23.

Here, the voice synthesizing unit 5 temporarily stores the voice information such as the standard voice pattern, the intensity of the sound, the pitch, and the voiceprint sent from the voice information storage unit 4 in the voice information storage means 51, and then the voice information is stored. The synthesizing means 52 performs speech synthesis. This voice synthesis synthesizes a standard voice pattern and voiceprint feature data from voice information, and further creates a synthesized voice that is completely demodulated by adding the dynamics of the voice and the pitch of the voice to the synthesized voice. After being stored in the storage unit 6, it is sent to the voice conversion output unit 7. The voice conversion output unit 7 reads the synthesized voice information stored in the voice storage unit 6, converts it into an analog signal capable of voice output, and outputs voice from the voice output means 13.

At this time, for example, when the voice is heard again by the other party, the unhealthy person operates the voice repeat switch 81 to read the synthesized voice information from the voice storage unit 6 again, and the voice conversion output unit 7 outputs the voice. Since the voice is output from the voice output means 13 after being converted into an analog signal that can be output, an appropriate voice signal, that is, the content of the conversation can be transmitted to the other party. Further, in the case where the speech speed of the unhealthy person is slow, it is easy for the unhealthy person or the like to hear by appropriately increasing the output speed of the sound signal by the sound speed varying device 82. Further, for example, in a place where there is a lot of external noise, the voice output level 13 can be increased by variably operating the voice strength variator 83.
Can be output, and similarly, a healthy person can easily hear.

Therefore, according to the configuration of the above embodiment, the mounting body 11 to be the main body of the voice input / output device 1 is made of cloth or the like having excellent sound absorbing property, so that it is wrapped around the neck of an unhealthy person. In addition to completely adapting itself to the sound when being played, it absorbs the voice uttered from the mouth and noise coming from the outside, and the voice input means 12 can appropriately input the vibration uttered from the throat. In addition, if the flat voice input means 12 and the voice output means 13 are attached to the surface of the wearing body 11 so as to be attached thereto, the weight is light and convenient for carrying, the pressure on the throat is eliminated, and the burden on the throat is reduced. Can be reduced. Further, the voice recognition unit 2 recognizes the characteristics of the voiceprint, the strength and weakness of the sound, the pitch of the sound, and the vocal sound from the vibration frequency signal input from the voice input unit 12, and recognizes the voice code of the vocal sound and the characteristics of the voiceprint and the sound. The strength and weakness information and the pitch information of the sound are sent to the voice code determination unit 3, where the voice code is compared with a large number of prestored voice codes, and when both voice codes match,
A standard voice pattern corresponding to words used in daily conversation such as "Thank you for the corresponding voice code" and "Goodbye" is read out, and the voice synthesizer 5 is accompanied by the features of the voiceprint, the strength of the sound, the pitch of the sound, and the like. Since the speech is transmitted, a long standard speech pattern, which is a daily conversation, can be output from the utterance of the first short conversation by the unhealthy person, and the burden of the conversation by the unhealthy person can be sufficiently assisted.

Further, in the voice synthesizing unit 5, after storing various voice information sent from the voice code judging unit 3 side, the features of the voiceprint are synthesized from the voice information into a standard voice pattern, and Since the strength of the sound and the pitch of the sound are added, it is possible to create a synthetic sound that includes the emotions of an unhealthy person.

Further, since the voice repeat switch 81 for repeatedly outputting the voice signal, the voice speed changer 82 for changing the speed and strength of the voice signal and the voice strength changer 83 are provided, the situation of the unhealthy person and the other side It is possible to output an appropriate audio signal while performing an appropriate operation according to the listening state.

In the above embodiment, the entire structure has been described. However, from the viewpoint of being easily carried and operated easily by an unhealthy person, the following divided structure is preferable. That is, the voice input / output device portion having the voice input means 12 and the voice output means 13, the voice recognition portion 2, the voice code determination portion 3, the voice information storage portion 4, the voice synthesis portion 5, the voice storage portion 6 and the voice conversion output. If it is divided into a device main body portion including a power source portion including the portion 7 and a voice output adjusting portion such as a voice repeat switch 81, a voice speed variable device 82 and a voice intensity variable device 83, the signal lines can be connected appropriately. If you do, wrap the audio input / output device around the neck and fix it,
The main body of the device can be hung on the waist and the audio output adjustment part can be held in the hand, which makes it easy to carry and improve operability.

Although the mounting body 11 is made of cloth, it is not particularly limited as long as it is a sound absorbing paper material or a similar material. In addition, the present invention can be modified in various ways without departing from the scope of the invention.

[0043]

As described above, according to the present invention, the following various effects are exhibited. According to the first aspect of the invention, even a person who cannot utter a voice from the mouth can reliably input a signal corresponding to the voice, and can properly input the throat vibration without pressing the throat of an unhealthy person.

According to the second and third aspects of the present invention, the unclear voice uttered by an unhealthy person can be correctly recognized, and the voice pattern, the voiceprint, and the strength of the sound are synthesized to synthesize the emotion of the person who utters the voice. Speech synthesis including can be realized.

Next, the invention of claim 4 can generate an appropriate voice signal by considering the physical condition of an unhealthy person and by appropriately performing voice operation according to the listening condition of the other person. . Further, according to the invention of claim 5, by appropriately dividing the configuration, an unhealthy person can easily wear it, and operability by the unhealthy person can be improved.

[Brief description of drawings]

FIG. 1 is a functional block diagram showing an embodiment of a portable voice recognition output assisting device according to the present invention.

FIG. 2 is a diagram showing a configuration of a voice input / output device shown in FIG.

FIG. 3 is a functional block diagram embodying the voice recognition unit shown in FIG.

FIG. 4 is a diagram illustrating voice recognition by a voice recognition unit.

5 is a functional block diagram embodying the voice code determination unit shown in FIG.

FIG. 6 is a functional block diagram embodying the voice synthesis unit shown in FIG. 1.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Voice input / output device, 2 ... Voice recognition unit, 3 ... Voice code determination unit, 4 ... Voice information storage unit, 5 ... Voice synthesis unit, 6 ... Voice storage unit, 7 ... Voice conversion output unit, 8 ... Voice output Adjustment unit, 1
1 ... Wearing body, 12 ... Voice input means, 13 ... Voice output means, 81 ... Voice repeat switch, 82 ... Voice speed variable device, 83 ... Voice intensity variable device.

Claims (5)

[Claims] 1. A vibration generated from the vibration generator is detected on the back side of a strip-shaped mounting body formed of a sound absorbing material that is wound around and fixed to the vibration generator and converted into an electrical vibration frequency signal. A voice input / output device having a flat voice output means for outputting a voice signal corresponding to the vibration frequency signal on the front surface side of the wearing body. Portable voice recognition output assist device. 2. A voice input means for detecting a vibration generated from a vibration generator and outputting an electrical vibration frequency signal, and a voice output for outputting a sound signal corresponding to the vibration frequency signal input by the voice input means. A voice input / output device having a means, a voice recognition unit for recognizing a voiceprint, sound intensity, pitch, and generated sound from a vibration frequency signal input from the voice input means, and a plurality of standard voice patterns and patterns in advance. A corresponding voice code is stored, the voice code relating to the generated sound recognized by the voice recognition unit is compared with the already stored voice code, and when both voice codes match, the voice code is corresponded to. And a voice code determination unit for reading out the standard voice pattern and outputting voice information including the standard voice pattern, the voiceprint, the strength of the sound, and the pitch. A portable voice recognition output assisting device. 3. The combination according to claim 2, wherein the standard voice pattern output from the voice code determination unit and the voice print are combined, and further, one or both of the strength and the low and high of the sound are added and combined. Portable voice recognition, characterized in that a voice synthesizing unit for producing a sound and a voice conversion output unit for converting the synthesized voice produced by the voice synthesizing unit into a voice signal and outputting the voice signal from the voice output means are added. Output auxiliary device. 4. The voice synthesis according to claim 2, wherein the standard voice pattern output from the voice code determination unit is synthesized with the voiceprint, and further, the strength and the pitch of the voice are added to create a synthesized voice. Section, a voice storage section for storing the synthesized voice created by the voice synthesis section, and a voice conversion output section for converting the synthesized voice stored in the voice storage section into a voice signal and outputting the voice signal from the voice output means. , A voice repeat switch for reading the synthetic sound stored in the voice storage unit and repeatedly outputting it from the voice output unit, and varying either or both of the speed and the strength of the voice signal output from the voice conversion output unit. A portable voice recognition output assisting device, which is characterized in that a voice varying means is added. 5. A voice input / output device portion having voice input means and voice output means, and a voice recognition section for recognizing a voiceprint, a sound intensity, a pitch, and a generated sound from a vibration frequency signal input from the voice input means. The voice code of the generated sound recognized by this voice recognition unit is compared with a plurality of voice codes stored in advance, and when both voice codes match, the standard voice pattern stored in advance corresponding to the voice code is determined. A voice code determination unit that reads out and generates voice information such as the standard voice pattern, the voiceprint, and sound intensity and pitch, a voice synthesis unit that synthesizes the standard voice pattern, voiceprint, sound intensity, pitch, and the like, and this voice synthesis. Stored in the voice storage unit; a main body device unit having a voice conversion output unit for converting the synthetic sound created by the unit into a voice signal and outputting the voice signal from the voice output unit. A voice repeat switch for reading a synthetic sound and repeatedly outputting it from the voice output means, and a voice adjusting portion having a voice varying means for varying one or both of the speed and the strength of the voice signal output from the voice conversion output section. A portable voice recognition output assisting device characterized by being divided into