JP6191747B2 - Speech analysis apparatus and speech analysis system - Google Patents

Description

  The present invention relates to a voice analysis device and a voice analysis system.

  Patent Document 1 discloses the following prior art. This prior art includes first and second omnidirectional microphones and voice / non-voice detection means for detecting voice and non-voice using the output signals from these omnidirectional microphones as inputs. The noise level is estimated from the output of the second microphone when there is no sound, and the output is amplified according to the noise level. Then, the output of the variable signal amplification means is subtracted from the output of the first omnidirectional microphone. In this way, the bidirectionality is changed when the noise is high, and the omnidirectionality and the directional characteristics are changed when the noise is low.

  Patent Document 2 discloses the following prior art. This prior art configures a headset to generate acoustically distinct audio signals within a noisy acoustic environment. The headset arranges a pair of microphones with a predetermined gap in the vicinity of the user's mouth. Each microphone receives the user's voice and further receives the noise of the acoustic environment. A microphone signal having both noise and information components is received in the separation process. The separation process produces a speech signal with substantially reduced noise components. The audio signal is then processed for transmission.

Japanese Patent Application Laid-Open No. 8-19196 Special table 2008-507926

  It is an object of the present invention to provide a speech analysis apparatus and system for acquiring speech by speech acquisition means and identifying a speaker based on the acquired non-linguistic information of speech.

The invention described in claim 1
A first voice acquisition means provided on a strap attached to the user;
The second sound acquisition means provided on the strap, wherein the distance of the sound wave propagation path from the user's mouth to the second sound acquisition means when the strap is hung on the neck is the use Second sound acquisition provided at a position smaller than the distance of the sound wave propagation path from the person's mouth to the first sound acquisition means and less than or equal to the distance between the second sound acquisition means and the first sound acquisition means Means, and
Using the result obtained from the distance relationship between the user's mouth, the first voice acquisition means, and the second voice acquisition means, the sound pressure of the voice acquired by the first voice acquisition means and the first 2. A speech analysis apparatus for identifying whether a sound generated by the user or a sound from a sound source other than the user from a sound pressure ratio with a sound pressure of sound acquired by the two sound acquisition means. .
The invention described in claim 2
The strap has a cylindrical structure,
2. The speech analysis apparatus according to claim 1, wherein the first voice acquisition unit and the second voice acquisition unit provided in the strap are provided inside the strap. 3.
The invention according to claim 3
The first sound acquisition means and the second sound acquisition means are a distance (La1) of a sound wave propagation path from the user's mouth to the first sound acquisition means and the second sound acquisition means from the user's mouth. The distance (La2) of the sound wave propagation path to
La1 ≒ 1.5 × La2-4 × La2
The speech analysis device according to claim 1, wherein the speech analysis device is provided in a distance relationship.
The invention according to claim 4
The sound pressure (G1) of the sound acquired by the first sound acquisition means and the sound pressure (G2) of the sound acquired by the second sound acquisition means are:
G2 / G1 <2
The speech analysis apparatus according to any one of claims 1 to 3, wherein the acquired sound is identified from the sound from the other sound source.
The invention described in claim 5
A first sound acquisition means and a second sound acquisition means arranged so that the distances of the sound wave propagation paths from the user's mouth are different positions;
Based on the sound pressure ratio between the sound pressure of the sound acquired by the first sound acquisition means and the sound pressure of the sound acquired by the second sound acquisition means, the first sound acquisition means and the second sound acquisition means An identification unit for identifying whether the acquired voice is a voice of a user of the first voice acquisition unit and the second voice acquisition unit or a voice from a sound source other than the user;
The second voice acquisition unit is a voice analysis device provided at a position where a distance from the user's mouth is equal to or less than a distance from the first voice acquisition unit.
The invention described in claim 6
The identification unit performs a filtering process on the voice signal acquired by the first voice acquisition unit and the voice signal acquired by the second voice acquisition unit, and removes noise from the acquired voice. The speech analysis apparatus according to claim 5, wherein the sound pressures are compared.
The invention described in claim 7
The first sound acquisition means and the second sound acquisition means are a distance (La1) of a sound wave propagation path from the user's mouth to the first sound acquisition means and the second sound acquisition means from the user's mouth. The distance (La2) of the sound wave propagation path to
La1 ≒ 1.5 × La2-4 × La2
The speech analysis apparatus according to claim 5, wherein the speech analysis apparatus is provided in a distance relationship.
The invention according to claim 8 provides:
The sound pressure (G1) of the sound acquired by the first sound acquisition means and the sound pressure (G2) of the sound acquired by the second sound acquisition means are:
G2 / G1 <2
The speech analysis apparatus according to claim 5, wherein the acquired speech is distinguished from the speech from the other sound source.
The invention according to claim 9 is:
A terminal device attached to the user;
A host device for obtaining information from the terminal device,
The terminal device
First voice acquisition means;
The distance of the sound wave propagation path from the user's mouth is different from that of the first sound acquisition unit, and the distance to the user's mouth is equal to or less than the distance to the first sound acquisition unit. A second voice acquisition means provided;
Regarding the sound pressure ratio of the sound acquired by the first sound acquisition means and the second sound acquisition means, the distance between the user's mouth and the first sound acquisition means, the user's mouth and the second From the distance relationship between the sound acquisition means, the distance between the sound source other than the user and the first sound acquisition means, and the distance between the other sound source and the second sound acquisition means An identification unit for identifying whether the sound acquired by the first sound acquisition unit and the second sound acquisition unit is the voice of the user wearing the terminal device or the sound from the other sound source using the obtained result When,
A transmission unit that transmits utterance information that is information about the audio signal acquired by the first audio acquisition unit and the second audio acquisition unit including the identification result by the identification unit to the host device;
The host device is
A receiving unit that receives the utterance information transmitted from a plurality of the terminal devices;
An accumulation unit that accumulates the utterance information received by the reception unit for each terminal device that has transmitted the utterance information;
An analysis unit for analyzing the utterance information stored in the storage unit;
An output unit for outputting an analysis result by the analysis unit;
A voice analysis system comprising:
The invention according to claim 10 is:
As one of the analyses, the analysis unit compares the utterance information acquired from a plurality of the terminal devices, and participates in a specific conversation based on time information related to the utterance included in the utterance information. The speech analysis system according to claim 9, wherein speech information of the user is identified.
The invention according to claim 11
The analysis unit extracts a feature of the conversation based on the degree of dialogue expressed by the number of changes of the speaker during the conversation and the variation in time until the speaker changes. A speech analysis system according to claim 9 or claim 10.
The invention according to claim 12
The analysis unit extracts a feature of a conversation based on a degree of listening expressed by a ratio between a speech time of each conversation participant in the speech information and a speech time of another person. The speech analysis system according to any one of claims 11 to 11.
The invention according to claim 13
10. The analysis unit extracts a feature of a conversation based on a conversation activity expressed by a ratio of a time when no conversation participant speaks with respect to the entire utterance information. The speech analysis system according to any one of 12.

According to the first aspect of the present invention, the speaker can be identified using the sound pressure ratio as the non-linguistic information of the recorded voice.
According to the second aspect of the present invention, it is expected that the user can wear the voice acquisition means without being aware of the presence of the voice acquisition means, compared to the case where the voice acquisition means is outside the strap.
According to the invention of claim 3, since the sound pressure ratio of the voice recorded by the first voice acquisition means and the second voice acquisition means is increased, the speaker identification system is improved.
According to the invention of claim 4, in the configuration in which the first voice acquisition means and the second voice acquisition means are provided on the strap, it is possible to accurately identify the speaker based on the sound pressure ratio of the recorded voice.
According to the invention of claim 5, the speaker can be identified using the sound pressure ratio as the non-linguistic information of the recorded voice.
According to the sixth aspect of the invention, the noise component is removed from the recorded voice, so that the discrimination performance of another person's speech is improved.
According to the invention of claim 7, since the sound pressure ratio of the voice recorded by the first voice acquisition means and the second voice acquisition means is increased, the speaker identification system is improved.
According to invention of Claim 8, in the structure which has the positional relationship from which the distance between a 2nd audio | voice acquisition means and a user's mouth becomes below the distance between a 2nd audio | voice acquisition means and a 1st audio | voice acquisition means Thus, it is possible to accurately identify the speaker based on the sound pressure ratio of the recorded voice.
According to the ninth aspect of the present invention, it is possible to analyze the utterance situation of a plurality of speakers.
According to the tenth aspect of the present invention, it is possible to extract utterance information related to a conversation by a specific speaker among utterance information of a plurality of speakers.
According to the eleventh aspect of the present invention, it is possible to perform an analysis based on the degree of dialogue regarding the utterance status of a plurality of speakers.
According to the twelfth aspect of the present invention, it is possible to perform an analysis based on the degree of listening regarding the utterance situation of a plurality of utterers.
According to the invention of claim 13, it is possible to perform an analysis based on the conversation activity level with respect to the utterance situation of a plurality of speakers.

It is a figure which shows the structural example of the audio | voice analysis system by this embodiment. It is a figure which shows the structural example of the terminal device in this embodiment. It is a figure which shows the positional relationship of a wearer and another person's mouth (speaking part), and a microphone. It is a figure which shows the relationship between the distance of the sound wave propagation path between a microphone and a sound source, and sound pressure (input sound volume). It is a figure which shows the identification method of a wearer's own speech voice and another person's speech sound. It is a flowchart which shows operation | movement of the terminal device in this embodiment. It is a figure which shows the condition where the several wearer who each mounted | wore with the terminal device of this embodiment is talking. It is a figure which shows the example of the speech information of each terminal device in the conversation condition of FIG. It is a figure which shows the function structural example of the host apparatus in this embodiment.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
<System configuration example>
FIG. 1 is a diagram illustrating a configuration example of a speech analysis system according to the present embodiment.
As shown in FIG. 1, the system of this embodiment includes a terminal device 10 and a host device 20. The terminal device 10 and the host device 20 are connected via a wireless communication line. As a type of the wireless communication line, a line based on an existing method such as Wi-Fi (trademark) (Wireless Fidelity), Bluetooth (trademark), ZigBee (trademark), or UWB (Ultra Wideband) may be used. In the illustrated example, only one terminal device 10 is described, but as will be described in detail later, the terminal device 10 is worn and used by each user and is actually used. As many terminal devices 10 as the number of persons are prepared. Hereinafter, a user wearing the terminal device 10 is referred to as a wearer.

  The terminal device 10 includes at least one set of microphones (first microphone 11 and second microphone 12) and an amplifier (first amplifier 13 and second amplifier 14) as voice acquisition means. Further, the terminal device 10 includes a voice analysis unit 15 that analyzes the recorded voice, a data transmission unit 16 that transmits the analysis result to the host device 20, and a power supply unit 17 as processing means.

  The first microphone 11 and the second microphone 12 are arranged at positions where the distance of the sound wave propagation path from the wearer's mouth (speaking part) (hereinafter simply referred to as “distance”) is different. Here, the first microphone 11 is arranged at a position (for example, about 35 cm) far from the mouth (speaking part) of the wearer, and the second microphone 12 is a position (for example, about 10 cm) near the mouth (speaking part) of the wearer. ). As the types of microphones used as the first microphone 11 and the second microphone 12 of the present embodiment, various existing types such as a dynamic type and a condenser type may be used. It is particularly preferable to use a non-directional MEMS (Micro Electro Mechanical Systems) type microphone.

  The first amplifier 13 and the second amplifier 14 amplify an electrical signal (audio signal) output by the first microphone 11 and the second microphone 12 according to the acquired sound. As the amplifier used as the first amplifier 13 and the second amplifier 14 of the present embodiment, an existing operational amplifier or the like may be used.

  The voice analysis unit 15 analyzes the voice signal output from the first amplifier 13 and the second amplifier 14. Then, it is identified whether the voice acquired by the first microphone 11 and the second microphone 12 is a voice uttered by the wearer wearing the terminal device 10 or a voice uttered by another person. That is, the voice analysis unit 15 functions as an identification unit that identifies a voice speaker based on the voice acquired by the first microphone 11 and the second microphone 12. Details of specific processing for speaker identification will be described later.

  The data transmission unit 16 transmits the acquired data including the analysis result by the voice analysis unit 15 and the ID of the terminal device 10 to the host device 20 via the wireless communication line. As information to be transmitted to the host device 20, in addition to the above analysis results, for example, the acquisition time of the sound by the first microphone 11 and the second microphone 12 and the acquired sound according to the contents of the processing performed in the host device 20 Information such as sound pressure may be included. In addition, the data storage part which accumulate | stores the analysis result by the audio | voice analysis part 15 may be provided in the terminal device 10, and the preservation | save data for a fixed period may be transmitted collectively. It may be transmitted via a wired line.

  The power supply unit 17 supplies power to the first microphone 11, the second microphone 12, the first amplifier 13, the second amplifier 14, the voice analysis unit 15, and the data transmission unit 16. As the power source, for example, an existing power source such as a dry battery or a rechargeable battery is used. Moreover, the power supply part 17 contains well-known circuits, such as a voltage conversion circuit and a charge control circuit, as needed.

  The host device 20 outputs a data reception unit 21 that receives data transmitted from the terminal device 10, a data storage unit 22 that stores the received data, a data analysis unit 23 that analyzes the stored data, and an analysis result. Output unit 24. The host device 20 is realized by an information processing device such as a personal computer. Further, as described above, a plurality of terminal devices 10 are used in the present embodiment, and the host device 20 receives data from each of the plurality of terminal devices 10.

  The data receiving unit 21 corresponds to the above-described wireless communication line, receives data from each terminal device 10, and sends it to the data storage unit 22. The data storage unit 22 is realized by a storage device such as a magnetic disk device of a personal computer, for example, and stores received data acquired from the data receiving unit 21 for each speaker. Here, the speaker is identified by collating the terminal ID transmitted from the terminal device 10 with the name of the speaker registered in advance in the host device 20 and the terminal ID. Further, the wearer name may be transmitted from the terminal device 10 instead of the terminal ID.

  The data analysis unit 23 is realized by a program-controlled CPU of a personal computer, for example, and analyzes data stored in the data storage unit 22. The specific analysis content and analysis method can take various contents and methods depending on the purpose and use of the system of the present embodiment. For example, the frequency of dialogue between wearers of the terminal device 10 and the tendency of each wearer's dialogue partner may be analyzed, or the relationship between the dialogues may be inferred from information on individual utterance length and sound pressure in the dialogue. Done.

  The output unit 24 outputs the analysis result from the data analysis unit 23 or performs output based on the analysis result. The output means can take various means such as a display display, a print output by a printer, and an audio output according to the purpose and use mode of the system, the contents and format of the analysis result, and the like.

<Configuration example of terminal device>
FIG. 2 is a diagram illustrating a configuration example of the terminal device 10.
As described above, the terminal device 10 is used by being attached to each user. In order for the user to be able to wear the terminal device 10 according to the present embodiment, as shown in FIG. 2, the terminal device 10 includes a device main body 30 and a strap 40 connected to the device main body 30. In the configuration shown in the figure, the user puts the neck through the strap 40 and hangs the apparatus main body 30 from the neck.

  The apparatus main body 30 is a thin rectangular parallelepiped case 31 made of metal, resin, or the like, and a circuit and a power source for realizing at least the first amplifier 13, the second amplifier 14, the voice analysis unit 15, the data transmission unit 16, and the power supply unit 17. The power supply (battery) of the unit 17 is accommodated. The case 31 may be provided with a pocket for inserting an ID card or the like displaying ID information such as the name and affiliation of the wearer. Further, such ID information or the like may be printed on the surface of the case 31 itself, or a sticker describing the ID information or the like may be attached.

  The strap 40 is provided with a first microphone 11 and a second microphone 12 (hereinafter referred to as microphones 11 and 12 when the first microphone 11 and the second microphone 12 are not distinguished). The microphones 11 and 12 are connected to the first amplifier 13 and the second amplifier 14 accommodated in the apparatus main body 30 by cables (electric wires or the like) passing through the inside of the strap 40. As the material of the strap 40, various existing materials such as leather, synthetic leather, cotton and other natural fibers and synthetic fibers such as resin, metal, etc. may be used. Moreover, the coating process using a silicon resin, a fluororesin, etc. may be given.

  The strap 40 has a cylindrical structure, and the microphones 11 and 12 are housed inside the strap 40. By providing the microphones 11 and 12 inside the strap 40, the microphones 11 and 12 are prevented from being damaged and dirty, and the conversation person is prevented from being aware of the presence of the microphones 11 and 12. Note that the first microphone 11 disposed at a position far from the wearer's mouth (speaking part) may be provided in the apparatus main body 30 by being incorporated in the case 31. In the present embodiment, a case where the first microphone 11 is provided on the strap 40 will be described as an example.

  Referring to FIG. 2, the first microphone 11 is provided at an end (for example, a position within 10 cm from the connection site) of the strap 40 connected to the apparatus main body 30. Thus, the first microphone 11 is disposed at a position about 30 cm to 40 cm away from the wearer's mouth (speaking part) in a state where the wearer hangs the strap 40 around the neck and lowers the apparatus main body 30. . Even when the first microphone 11 is provided in the apparatus main body 30, the distance from the wearer's mouth (speaking part) to the first microphone 11 is approximately the same.

  The second microphone 12 is provided at a position away from the end of the strap 40 connected to the device main body 30 (for example, a position of about 20 cm to 30 cm from the connection site). Thus, the second microphone 12 is positioned at the wearer's neck (for example, a position corresponding to the clavicle) in a state where the wearer hangs the strap 40 on the neck and the apparatus main body 30 is lowered. From about 10 cm to 20 cm.

  In addition, the terminal device 10 of this embodiment is not limited to the structure shown in FIG. For example, in the microphones 11 and 12, the distance (of the sound wave propagation path) from the first microphone 11 to the wearer's mouth (speech part) is the sound wave propagation path from the second microphone 12 to the wearer's mouth (speech part). The positional relationship between the first microphone 11 and the second microphone 12 may be specified so as to be several times the distance. Therefore, the first microphone 11 may be provided on the strap 40 on the back side of the neck. Further, the microphones 11 and 12 are not limited to the configuration provided on the strap 40 as described above, and may be attached to the wearer by various methods. For example, each of the first microphone 11 and the second microphone 12 may be configured to be individually fixed to clothes using pins or the like. Alternatively, a dedicated mounting tool designed so that the positional relationship between the first microphone 11 and the second microphone 12 is fixed at a desired position may be prepared and mounted.

  Further, as shown in FIG. 2, the apparatus main body 30 is not limited to the configuration that is connected to the strap 40 and is provided from the wearer's neck, but may be configured as an apparatus that can be easily carried. For example, instead of the strap as in the present embodiment, it may be configured to be attached to clothes or a body with a clip or a belt, or may be configured to be simply carried in a pocket or the like. In addition, a function of receiving, amplifying, and analyzing a voice signal from the microphones 11 and 12 may be realized in a mobile phone or other existing portable electronic information terminal. However, when the first microphone 11 is provided in the apparatus main body 30, it is necessary to maintain the positional relationship between the first microphone 11 and the second microphone 12 as described above. Identified.

  Furthermore, the microphones 11 and 12 and the apparatus main body 30 (or the voice analysis unit 15) may be connected by wireless communication instead of being connected by wire. The first amplifier 13, the second amplifier 14, the voice analysis unit 15, the data transmission unit 16, and the power supply unit 17 are accommodated in a single case 31 in the above configuration example, but are divided into a plurality of individuals. It may be configured. For example, the power supply unit 17 may be used by being connected to an external power supply without being stored in the case 31.

<Identification of speakers (self and others) based on non-linguistic information of recorded speech>
Next, a speaker identification method according to this embodiment will be described.
The system according to the present embodiment distinguishes between the speech voice of the wearer of the terminal device 10 and the speech voice of the other person using the voice information recorded by the two microphones 11 and 12 provided in the terminal device 10. To do. In other words, the present embodiment identifies one another from the other regarding the speaker of the recorded voice. Further, in the present embodiment, the utterance is based on non-linguistic information such as sound pressure (input volume to the microphones 11 and 12), not linguistic information obtained by using morphological analysis or dictionary information, among recorded voice information. Identify the person. In other words, the voice speaker is identified not from the utterance content specified by the linguistic information but from the utterance situation specified by the non-linguistic information.

  As described with reference to FIGS. 1 and 2, in the present embodiment, the first microphone 11 of the terminal device 10 is disposed at a position far from the mouth (speaking site) of the wearer, and the second microphone 12 is the wearer. It is arranged at a position close to the mouth (speaking part). That is, if the wearer's mouth (speaking part) is a sound source, the distance between the first microphone 11 and the sound source and the distance between the second microphone 12 and the sound source are greatly different. Specifically, the distance between the first microphone 11 and the sound source is about 1.5 to 4 times the distance between the second microphone 12 and the sound source. Here, the sound pressure of the recorded sound in the microphones 11 and 12 is attenuated (distance attenuation) as the distance between the microphones 11 and 12 and the sound source increases. Therefore, regarding the voice of the wearer, the sound pressure of the recorded sound in the first microphone 11 and the sound pressure of the recorded sound in the second microphone 12 are greatly different.

  On the other hand, considering the case where the mouth (speaking part) of a person other than the wearer (other person) is used as the sound source, since the other person is away from the wearer, the distance between the first microphone 11 and the sound source, The distance between the second microphone 12 and the sound source does not change greatly. Depending on the position of the other person with respect to the wearer, a difference between both distances may occur, but the distance between the first microphone 11 and the sound source is the second as in the case where the mouth (speaking part) of the wearer is used as the sound source. It is never several times the distance between the microphone 12 and the sound source. Therefore, regarding the voice of other person, the sound pressure of the recorded voice in the first microphone 11 and the sound pressure of the recorded voice in the second microphone 12 do not differ greatly as in the case of the voice of the wearer.

FIG. 3 is a diagram illustrating a positional relationship between the mouths (speaking parts) of the wearer and the other person and the microphones 11 and 12.
In the relationship shown in FIG. 3, let La1 be the distance between the sound source a that is the mouth (speaking part) of the wearer and the first microphone 11, and let La2 be the distance between the sound source a and the second microphone 12. Further, the distance between the sound source b, which is the mouth (speaking part) of the other person, and the first microphone 11 is Lb1, and the distance between the sound source b and the second microphone 12 is Lb2. In this case, the following relationship holds.
La1> La2 (La1≈1.5 × La2 to 4 × La2)
Lb1≈Lb2

FIG. 4 is a diagram illustrating the relationship between the distance between the microphones 11 and 12 and the sound source and the sound pressure (input sound volume).
As described above, the sound pressure is attenuated according to the distance between the microphones 11 and 12 and the sound source. In FIG. 4, when the sound pressure Ga1 at the distance La1 and the sound pressure Ga2 at the distance La2 are compared, the sound pressure Ga2 is about four times the sound pressure Ga1. On the other hand, since the distance Lb1 and the distance Lb2 are approximate, the sound pressure Gb1 in the case of the distance Lb1 and the sound pressure Gb2 in the case of the distance Lb2 are substantially equal. Therefore, in the present embodiment, the difference between the sound pressure ratios is used to distinguish between the wearer's own speech and the other's speech in the recorded speech. In the example shown in FIG. 4, the distances Lb1 and Lb2 are 60 cm. However, here, it is meaningful that the sound pressure Gb1 and the sound pressure Gb2 are substantially equal, and the distances Lb1 and Lb2 are limited to the illustrated values. Not.

FIG. 5 is a diagram showing a method for discriminating between the wearer's own speech and the other's speech.
As described with reference to FIG. 4, the sound pressure Ga <b> 2 of the second microphone 12 is several times (for example, about four times) the sound pressure Ga <b> 1 of the first microphone 11 with respect to the voice of the wearer himself / herself. Further, regarding the voice of another person, the sound pressure Gb2 of the second microphone 12 is substantially equal to the sound pressure Gb1 of the first microphone 11 (about 1 time). Therefore, in the present embodiment, a threshold is set for the ratio between the sound pressure of the second microphone 12 and the sound pressure of the first microphone 11. Then, the voice whose sound pressure ratio is larger than the threshold is determined as the voice of the wearer, and the voice whose sound pressure ratio is lower than the threshold is determined as the voice of the other person. In the example shown in FIG. 5, the threshold value is 2, and the sound pressure ratio Ga2 / Ga1 exceeds the threshold value 2, so that it is determined as the wearer's own speech sound, and the sound pressure ratio Gb2 / Gb1 is smaller than the threshold value 2 so It is judged.

  By the way, the sound recorded by the microphones 11 and 12 includes so-called noise such as environmental sound in addition to the speech sound. The relationship of the distance between the noise source and the microphones 11 and 12 is similar to the case of the speech of another person. That is, according to the examples shown in FIGS. 4 and 5, the distance between the noise source c and the first microphone 11 is Lc1, and the distance between the noise source c and the second microphone 12 is Lc2. Then, the distance Lc1 and the distance Lc2 are approximated. The sound pressure ratio Gc2 / Gc1 in the recorded voices of the microphones 11 and 12 is smaller than the threshold value 2. However, such noise is separated and removed from the uttered voice by performing a filtering process using an existing technique using a bandpass filter, a gain filter, or the like.

<Operation example of terminal device>
FIG. 6 is a flowchart showing the operation of the terminal device 10 in the present embodiment.
As shown in FIG. 6, when the microphones 11 and 12 of the terminal device 10 acquire sound, electrical signals (audio signals) corresponding to the acquired sounds are transmitted from the microphones 11 and 12 to the first amplifier 13 and the second amplifier 14. (Step 601). When acquiring the audio signal from the microphones 11 and 12, the first amplifier 13 and the second amplifier 14 amplify the signal and send it to the audio analysis unit 15 (step 602).

  The voice analysis unit 15 performs a filtering process on the signals amplified by the first amplifier 13 and the second amplifier 14, and removes noise components such as environmental sounds from the signals (step 603). Next, the voice analysis unit 15 records each of the microphones 11 and 12 every certain time unit (for example, tens of seconds to hundreds of seconds) with respect to the signal from which the noise component has been removed. An average sound pressure in the voice is obtained (step 604).

  When there is a gain of the average sound pressure in each of the microphones 11 and 12 obtained in step 604 (Yes in step 605), the voice analysis unit 15 determines that there is an utterance voice (utterance has been performed), and then A ratio (sound pressure ratio) between the average sound pressure in the first microphone 11 and the average sound pressure in the second microphone 12 is obtained (step 606). If the sound pressure ratio obtained in step 606 is greater than the threshold (Yes in step 607), the voice analysis unit 15 determines that the uttered voice is a voice generated by the wearer's own utterance (step 608). If the sound pressure ratio obtained in step 606 is smaller than the threshold value (No in step 607), the voice analysis unit 15 determines that the uttered voice is a voice of another person's utterance (step 609).

  On the other hand, when there is no gain of the average sound pressure in each of the microphones 11 and 12 obtained in step 604 (No in step 605), the voice analysis unit 15 determines that there is no uttered voice (no utterance is performed) ( Step 610). Note that the determination in step 605 takes into account the case where noise that could not be removed by the filtering process in step 603 remains in the signal, and if there is a gain when the gain value of the average sound pressure is greater than or equal to a certain value. You may judge.

  Thereafter, the voice analysis unit 15 causes the data transmission unit 16 to transmit the information (the presence / absence of the utterance, information of the utterer) obtained by the processing of Steps 604 to 610 to the host device 20 as an analysis result ( Step 611). At this time, the length of the utterance time for each speaker (the wearer himself or another person), the gain value of the average sound pressure, and other additional information may be transmitted to the host device 20 together with the analysis result.

  In the present embodiment, the sound pressure of the first microphone 11 and the sound pressure of the second microphone 12 are compared to determine whether the speech sound is the sound of the wearer's own speech or the speech of another person's speech. . However, the speaker identification according to the present embodiment may be performed based on non-linguistic information extracted from the speech signals themselves acquired by the microphones 11 and 12, and is not limited to the comparison of sound pressures. For example, the voice acquisition time (voice signal output time) in the first microphone 11 and the voice acquisition time in the second microphone 12 may be compared. In this case, the spoken voice of the wearer has a large difference between the distance from the wearer's mouth (speaking part) to the first microphone 11 and the distance from the wearer's mouth (speaking part) to the second microphone 12. Therefore, a certain difference (time difference) occurs in the voice acquisition time. On the other hand, since the voice of the other person has a small difference between the distance from the wearer's mouth (speaking part) to the first microphone 11 and the distance from the wearer's mouth (speaking part) to the second microphone 12, The time difference of the voice acquisition time is smaller than that of the wearer's voice. Therefore, a threshold is set for the time difference of the voice acquisition time, and when the time difference of the voice acquisition time is larger than the threshold, it is determined that the wearer utters himself. You may make it judge that it is an utterance of others.

<System application examples and host device functions>
In the system of the present embodiment, information related to utterances (hereinafter referred to as utterance information) obtained as described above by a plurality of terminal devices 10 is collected in the host device 20. The host device 20 uses the information obtained from the plurality of terminal devices 10 to perform various analyzes according to the usage purpose and usage mode of the system. Hereinafter, an example in which this embodiment is used as a system for acquiring information related to communication of a plurality of wearers will be described.

FIG. 7 is a diagram illustrating a situation in which a plurality of wearers each wearing the terminal device 10 of the present embodiment are talking. FIG. 8 is a diagram illustrating an example of utterance information of the terminal devices 10A and 10B in the conversation state of FIG.
As shown in FIG. 7, consider a case where two wearers A and B who wear the terminal device 10 are talking. At this time, the voice recognized as the utterance of the wearer in the terminal device 10A of the wearer A is recognized as the utterance of the other person in the terminal device 10B of the wearer B. On the other hand, the voice recognized as the utterance of the wearer in the terminal device 10B is recognized as the utterance of the other person in the terminal device 10A.

  The utterance information is sent to the host device 20 independently from the terminal device 10A and the terminal device 10B. At this time, the utterance information acquired from the terminal device 10A and the utterance information acquired from the terminal device 10B are opposite in the identification result of the speaker (wearer and other person) as shown in FIG. Information indicating the utterance status such as the length of time and the timing when the speaker is switched is approximated. Therefore, the host device 20 of this application example compares the information acquired from the terminal device 10A and the information acquired from the terminal device 10B to determine that these information indicate the same utterance situation, and wearers Recognizing that A and the wearer B are talking. Here, the information indicating the utterance state includes at least the length of the utterance time in each utterance for each utterer described above, the start time and end time of each utterance, and the time (timing) at which the utterer is switched. As described above, the time information related to the utterance is used. Note that in order to determine the utterance situation related to a specific conversation, only part of the time information related to these utterances may be used, or other information may be additionally used.

FIG. 9 is a diagram illustrating a functional configuration example of the host device 20 in the application example.
In this application example, the host device 20 detects the utterance information (hereinafter, conversation information) from the terminal device 10 of the wearer who is having a conversation among the utterance information acquired from the terminal device 10. And a conversation information analysis unit 202 that analyzes the detected conversation information. The conversation information detection unit 201 and the conversation information analysis unit 202 are realized as functions of the data analysis unit 23.

  Speech information is also sent to the host device 20 from terminal devices 10 other than the terminal devices 10A and 10B. The utterance information from each terminal device 10 received by the data receiving unit 21 is stored in the data storage unit 22. Then, the conversation information detection unit 201 of the data analysis unit 23 reads the utterance information of each terminal device 10 stored in the data storage unit 22 and detects the conversation information that is utterance information related to a specific conversation.

  As shown in FIG. 8, the utterance information of the terminal device 10A and the utterance information of the terminal device 10B are extracted with characteristic correspondences different from the utterance information of the other terminal devices 10. The conversation information detection unit 201 compares the utterance information acquired from each terminal device 10 stored in the data storage unit 22, and determines the correspondence as described above from the utterance information acquired from the plurality of terminal devices 10. The utterance information is detected and identified as conversation information related to the same conversation. Since the utterance information is sent from the plurality of terminal devices 10 to the host device 20 at any time, the conversation information detection unit 201 performs the above-described processing while sequentially separating the utterance information for a predetermined time, for example, and performs a specific conversation. It is determined whether or not the conversation information related to is included.

  Note that the condition for the conversation information detection unit 201 to detect conversation information related to a specific conversation from the utterance information of the plurality of terminal devices 10 is not limited to the correspondence relationship illustrated in FIG. 8 described above. You may detect by what kind of technique which can identify the conversation information which concerns on a specific conversation from several utterance information.

  In the above example, an example is shown in which two wearers each wearing the terminal device 10 are talking, but the number of participants in the conversation is not limited to two. When three or more wearers are having a conversation, the terminal device 10 worn by each wearer recognizes the voice of the wearer of the own device as the voice of the wearer himself and the other (two This is distinguished from the above speech. However, information indicating the utterance status such as the utterance time and the timing at which the speaker is switched is approximated between the pieces of acquired information in each terminal device 10. Therefore, the conversation information detection unit 201 detects the utterance information acquired from the terminal device 10 of the wearer participating in the same conversation, and does not participate in the conversation, as in the case of the conversation between the two persons. It is distinguished from the utterance information acquired from the terminal device 10 of the wearer.

  Next, the conversation information analysis unit 202 analyzes the conversation information detected by the conversation information detection unit 201 and extracts features of the conversation. In the present embodiment, as a specific example, the features of the conversation are extracted based on three kinds of evaluation criteria of the degree of dialogue, the degree of listening, and the degree of conversation activity. Here, the degree of dialogue represents the balance of the speech frequency of conversation participants. The degree of listening represents the degree of listening to another person's speech in each conversation participant. The conversation activity level represents the density of speech in the entire conversation.

  The degree of dialogue is specified by the variation in the number of changes of the speaker during the conversation and the time until the speaker changes (the time during which one speaker speaks continuously). This is obtained from the number of times the speaker is switched and the time when the speaker is switched in the conversation information for a certain period of time. It is assumed that the value (level) of the degree of interaction is larger as the number of times the speaker is changed and the variation in the continuous utterance time of each speaker is smaller. This evaluation criterion is common to all the conversation information related to the same conversation (the utterance information of each terminal device 10).

The degree of listening is specified by the ratio between the speech time of each conversation participant in the conversation information and the speech time of others. For example, in the case of the following equation, it is assumed that the greater the value, the greater the value (level) of the listening degree.
Listening degree = (Speaking time of others) ÷ (Speaking time of wearer)
This evaluation criterion is different for each piece of utterance information acquired from the terminal device 10 of each conversation participant, even for conversation information related to the same conversation.

  The conversation activity is an index representing the so-called conversation excitement, and is specified by the ratio of the silent time (the time during which no conversation participant speaks) to the entire conversation information. The shorter the total silent time is, it means that one of the conversation participants is speaking in the conversation, and the conversation activity value (level) is large. This evaluation criterion is common to all the conversation information related to the same conversation (the utterance information of each terminal device 10).

  As described above, by analyzing the conversation information by the conversation information analysis unit 202, the features of the conversation related to the conversation information are extracted. In addition, the above analysis specifies how each participant participates in the conversation. Note that the above evaluation criteria are merely examples of information representing the characteristics of conversation, and the purpose and use of the system of this embodiment can be achieved by adopting other evaluation items or adding weights to each item. You may set the evaluation criteria according to an aspect.

  By performing the above analysis on various conversation information detected by the conversation information detection unit 201 from the utterance information stored in the data storage unit 22, the entire group of wearers of the terminal device 10 is analyzed. Can analyze communication trends. Specifically, for example, by examining the correlation between the number of conversation participants, the time during which the conversation was conducted, the degree of interaction, the degree of activity, and the frequency of occurrence of conversation, It is determined whether there is a tendency for the conversation of the aspect to be performed.

  Further, by performing the above analysis on a plurality of pieces of conversation information of a specific wearer, it is possible to analyze the communication tendency of the wearer. The way in which a specific wearer participates in a conversation may have a certain tendency depending on conditions such as the number of conversation partners and the number of conversation participants. Therefore, by examining a plurality of conversation information for a specific wearer, for example, features such as a high conversation level in a conversation with a specific partner, and a greater listening degree as the number of conversation participants increases are detected. Is expected to be.

  The utterance information identification process and the conversation information analysis process described above are merely examples of application of the system according to the present embodiment, and the purpose of use and usage of the system according to the present embodiment, the function of the host device 20, etc. Not what you want. A processing function for executing various analyzes and investigations on the utterance information acquired by the terminal device 10 of the present embodiment can be realized as a function of the host device 20.

DESCRIPTION OF SYMBOLS 10 ... Terminal device, 11 ... 1st microphone, 12 ... 2nd microphone, 13 ... 1st amplifier, 14 ... 2nd amplifier, 15 ... Voice analysis part, 16 ... Data transmission part, 17 ... Power supply part, 20 ... Host apparatus , 21 ... Data receiving unit, 22 ... Data accumulating unit, 23 ... Data analyzing unit, 24 ... Output unit, 30 ... Device main body, 40 ... Strap, 201 ... Conversation information detecting unit, 202 ... Conversation information analyzing unit

Claims (13)

A first voice acquisition means provided on a strap attached to the user;
The second sound acquisition means provided on the strap, wherein the distance of the sound wave propagation path from the user's mouth to the second sound acquisition means when the strap is hung on the neck is the use Second sound acquisition provided at a position smaller than the distance of the sound wave propagation path from the person's mouth to the first sound acquisition means and less than or equal to the distance between the second sound acquisition means and the first sound acquisition means Means, and
Using the result obtained from the distance relationship between the user's mouth, the first voice acquisition means, and the second voice acquisition means, the sound pressure of the voice acquired by the first voice acquisition means and the first 2. A speech analysis apparatus for identifying whether a sound generated by the user or a sound from a sound source other than the user from a sound pressure ratio with a sound pressure of sound acquired by the two sound acquisition means. The strap has a cylindrical structure,
The speech analysis apparatus according to claim 1, wherein the first voice acquisition unit and the second voice acquisition unit provided in the strap are provided in the strap. The first sound acquisition means and the second sound acquisition means are a distance (La1) of a sound wave propagation path from the user's mouth to the first sound acquisition means and the second sound acquisition means from the user's mouth. The distance (La2) of the sound wave propagation path to
La1 ≒ 1.5 × La2-4 × La2
The speech analysis apparatus according to claim 1, wherein the speech analysis apparatus is provided in a distance relationship. The sound pressure (G1) of the sound acquired by the first sound acquisition means and the sound pressure (G2) of the sound acquired by the second sound acquisition means are:
G2 / G1 <2
The speech analysis apparatus according to any one of claims 1 to 3, wherein the acquired speech is distinguished from speech from the other sound source. A first sound acquisition means and a second sound acquisition means arranged so that the distances of the sound wave propagation paths from the user's mouth are different positions;
Based on the sound pressure ratio between the sound pressure of the sound acquired by the first sound acquisition means and the sound pressure of the sound acquired by the second sound acquisition means, the first sound acquisition means and the second sound acquisition means An identification unit for identifying whether the acquired voice is a voice of a user of the first voice acquisition unit and the second voice acquisition unit or a voice from a sound source other than the user;
The voice analysis apparatus, wherein the second voice acquisition unit is provided at a position where a distance from the user's mouth is equal to or less than a distance from the first voice acquisition unit.   The identification unit performs a filtering process on the voice signal acquired by the first voice acquisition unit and the voice signal acquired by the second voice acquisition unit, and removes noise from the acquired voice. The speech analysis apparatus according to claim 5, wherein the sound pressures are compared. The first sound acquisition means and the second sound acquisition means are a distance (La1) of a sound wave propagation path from the user's mouth to the first sound acquisition means and the second sound acquisition means from the user's mouth. The distance (La2) of the sound wave propagation path to
La1 ≒ 1.5 × La2-4 × La2
The speech analysis apparatus according to claim 5, wherein the speech analysis apparatus is provided in a distance relationship. The sound pressure (G1) of the sound acquired by the first sound acquisition means and the sound pressure (G2) of the sound acquired by the second sound acquisition means are:
G2 / G1 <2
The speech analysis apparatus according to claim 5, wherein the acquired speech is identified as speech from the other sound source. A terminal device attached to the user;
A host device for obtaining information from the terminal device,
The terminal device
First voice acquisition means;
The distance of the sound wave propagation path from the user's mouth is different from that of the first sound acquisition unit, and the distance to the user's mouth is equal to or less than the distance to the first sound acquisition unit. A second voice acquisition means provided;
Regarding the sound pressure ratio of the sound acquired by the first sound acquisition means and the second sound acquisition means, the distance between the user's mouth and the first sound acquisition means, the user's mouth and the second From the distance relationship between the sound acquisition means, the distance between the sound source other than the user and the first sound acquisition means, and the distance between the other sound source and the second sound acquisition means An identification unit for identifying whether the sound acquired by the first sound acquisition unit and the second sound acquisition unit is the voice of the user wearing the terminal device or the sound from the other sound source using the obtained result When,
A transmission unit that transmits utterance information that is information about the audio signal acquired by the first audio acquisition unit and the second audio acquisition unit including the identification result by the identification unit to the host device;
The host device is
A receiving unit that receives the utterance information transmitted from a plurality of the terminal devices;
An accumulation unit that accumulates the utterance information received by the reception unit for each terminal device that has transmitted the utterance information;
An analysis unit for analyzing the utterance information stored in the storage unit;
An output unit for outputting an analysis result by the analysis unit;
A speech analysis system comprising:   As one of the analyses, the analysis unit compares the utterance information acquired from a plurality of the terminal devices, and participates in a specific conversation based on time information related to the utterance included in the utterance information. The speech analysis system according to claim 9, wherein speech information of the user is identified.   The analysis unit extracts a feature of the conversation based on the degree of dialogue expressed by the number of changes of the speaker during the conversation and the variation in time until the speaker changes. The speech analysis system according to claim 9 or 10.   The analysis unit extracts a feature of a conversation based on a degree of listening expressed by a ratio between a speech time of each conversation participant in the speech information and a speech time of another person. The speech analysis system according to any one of claims 11 to 11.   10. The analysis unit extracts a feature of a conversation based on a conversation activity expressed by a ratio of a time when no conversation participant speaks with respect to the entire utterance information. The speech analysis system according to any one of 12.

Images