JP2019146055A - Telephone call device and control method therefor - Google Patents

Abstract

To give a native utterer and a non-native utterer an easy telephone call without need for using manual switch or the like.SOLUTION: A telephone call device 21 determines whether a first speaker X is a native utterer or a language learner on the basis of at least a voice of the first speaker X and on the basis of the determination result, executes slow reproduction processing as predetermined voice processing for a language learner for a voice signal (equivalent to a voice of a second speaker Y) output to the first speaker X determined to be a language learner.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a call device and a control method for the call device.

  As a communication device that allows multiple speakers to talk, voice signals for the utterances of native speakers (referred to as native speakers) are spoken by non-native speakers (referred to as non-native speakers or language learners). A conference support apparatus is disclosed that delays the audio signal from the voice signal for the above (see, for example, Patent Document 1). In this conference support apparatus, a method for providing a terminal for a native speaker and a terminal for a non-native speaker in advance, or a speaker manually sets each terminal as a native speaker terminal or a non-native speaker terminal using a switch or the like. It is possible to determine whether or not it is a voice signal of a native speaker by a method or the like.

JP 2014-086832 A

However, the conventional configuration requires the production of separate terminals for native speakers and non-native speakers, and manual switches that switch the terminal for native speakers or non-native speakers. There are limitations. For this reason, the situation where it is difficult to apply the function of the conventional meeting assistance apparatus to the hands-free apparatus mounted in a vehicle etc. arises, for example.
Therefore, an object of the present invention is to make it easy for a native speaker and a non-native speaker to talk without using a manual switch or the like.

  In order to achieve the above object, the present invention provides a communication device that inputs and outputs audio signals corresponding to the voices of the respective speakers so that a plurality of speakers can talk to each other, based on at least the voices of the speakers, A determination unit that determines whether the speaker is a first speaker equivalent to a native speaker or a second speaker equivalent to a language learner, and the second speaker based on the determination result of the determination unit And a voice processing unit that performs predetermined voice processing for language learners on a voice signal output to a speaker determined to be.

  In the above configuration, the determination unit obtains predetermined frequency information capable of specifying the speaker's mother tongue from the speaker's voice, specifies the mother tongue based on the acquired frequency information, and uses the specified mother tongue And you may perform the 1st determination process which determines whether it is said 1st speaker or said 2nd speaker.

  Further, in the above configuration, the predetermined frequency information is a 0th formant frequency, and the determination unit is classified by language that associates a plurality of types of languages with a 0th formant frequency of a person whose native language is each language. The native language may be specified based on the frequency information.

  Further, in the above configuration, the speaker that can be regarded as the user of the user-fixed device using the language set in the user-fixed device that the call device uses for the call is the first speaker or the second speaker. You may perform the 2nd determination process which determines whether it is a speaker.

  In the above configuration, in the second determination process, when the language set in the user-fixed device matches the language set in the in-vehicle device connected to the call device, the language is set as the native language. If it is identified and does not match, the language set in the user-fixed device is identified as a native language, and the identified native language is used to determine whether the first speaker or the second speaker is used. Also good.

  Further, in the above configuration, the determination unit acquires information on a silent portion of the voice from the voice of the speaker, and whether the first speaker or the second speaker is based on the acquired information. You may perform the 3rd determination process which determines.

  Moreover, in the said structure, when the determination result of said 1st-3rd determination process differs, you may determine whether it is said 1st speaker or a 2nd speaker according to a predetermined priority.

  Further, in the above configuration, the call device is configured to collect a voice of a predetermined speaker among the plurality of speakers and a voice of another speaker toward the predetermined speaker. A sound output unit that emits sound, and the sound processing unit is configured to output sound corresponding to the sound to be emitted by the sound output unit when the predetermined speaker is determined to be the second speaker. The signal may be subjected to predetermined speech processing for language learners.

In the above configuration, the call device may be a hands-free call device used by the predetermined speaker for a hands-free call.
Further, in the above configuration, a storage unit that stores a telephone number of the other speaker determined to be the second speaker is provided, and the telephone number of the other speaker is stored in the memory at the start of a call. The voice processing unit performs predetermined voice processing for a language learner on the voice signal output to the other speaker without making the determination. May be.

  Further, in a control method for a communication device for inputting / outputting a voice signal corresponding to each speaker's voice so that a plurality of speakers can talk to each other, the speaker can speak a native language based on at least the voice of the speaker. A determination step for determining whether the speaker is a first speaker equivalent to a speaker or a second speaker corresponding to a language learner, and a story determined to be the second speaker based on the determination result of the determination step A voice processing step for performing predetermined voice processing for a language learner on a voice signal output to the learner.

  According to the present invention, it is possible to facilitate communication between a native speaker and a non-native speaker without using a manual switch or the like.

It is the figure which showed the structure of the telephone call system containing the telephone apparatus which concerns on 1st embodiment of this invention. It is the figure which showed an example of the relationship between several types of languages and the 0th formant frequency of the person who uses each language as a mother tongue. It is a flowchart which shows operation | movement of the communication apparatus with respect to the speaker (1st speaker X) by the side of a vehicle. It is a flowchart which shows operation | movement of the telephone call apparatus with respect to the speaker (2nd speaker Y) outside a vehicle. It is a flowchart explaining operation | movement of the telephone apparatus which concerns on 2nd embodiment.

Embodiments of the present invention will be described below with reference to the drawings.
(First embodiment)
FIG. 1 is a diagram showing a configuration of a call system 10 including a call device 21 according to the first embodiment of the present invention.
The call device 21 is a hands-free call device that is disposed in a vehicle such as an automobile and is used by a user (predetermined speaker) who is an occupant of the vehicle to perform a so-called hands-free call. The call device 21 includes a communication module 22 for wireless communication with a device having a wireless communication function. The communication device 21 communicates with another telephone terminal 25 via the telephone network by wirelessly communicating with a mobile phone 23 (also referred to as a telephone terminal) owned by the user by the communication module 22. As a result, a voice signal for a call is input / output between the call device 21 and the other telephone terminal 25.

The communication module 22 is a communication module for performing short-range wireless communication according to the Bluetooth (registered trademark) standard. Note that short-range wireless communication other than Bluetooth may be performed.
The mobile phone 23 has a function of communicating with other mobile phones and fixed phones via a mobile communication network (not shown). In addition to a built-in speaker, a built-in microphone, and a communication unit for telephone communication, A communication module for performing near field communication is provided. The mobile phone 23 and the communication device 21 are not limited to being connected wirelessly, and may be configured to be connected by wire.

  An in-vehicle device 27 is disposed in the vehicle, and this in-vehicle device 27 is connected to the communication device 21 so as to be communicable. The in-vehicle device 27 is a device having a navigation function, a radio reception function, an audio playback function, or the like, and the call device 21 inputs various instructions to the call device 21 through an operation panel of the in-vehicle device 27, for example. To do. Note that the communication device 21 and the in-vehicle device 27 may be configured integrally.

  Here, the mobile phone 23 and the in-vehicle device 27 are set with languages (hereinafter referred to as setting languages) 23A and 27A used for displaying the devices 23 and 27 and the like. Usually, the setting language 23A of the mobile phone 23 is set by the owner of the mobile phone 23, and the setting language 27A of the in-vehicle device 27 is set by the owner of the vehicle. Note that the owner of the mobile phone 23 and the owner of the vehicle may or may not match.

As shown in FIG. 1, in the communication device 21, the control unit 31 includes a CPU and functions as a computer that controls each unit of the communication device 21. The storage unit 32 stores a control program executed by the control unit 31 and various data.
The microphone 33 functions as a sound collection unit that collects the sound of a speaker who is a user of the call device 21 (hereinafter referred to as the first speaker X) (corresponding to a transmitted sound during a hands-free call). The speaker 35 functions as a sound emitting unit that emits the sound of a speaker (hereinafter referred to as a second speaker Y) who is a user of another telephone terminal 25 toward the first speaker X in the vehicle. . Note that the microphone 33 and the speaker 35 may be a microphone and a speaker dedicated to the telephone device, or may be a microphone and a speaker that the in-vehicle device 27 or the like uses for voice input / output.

  The first detection unit 41 detects the formant frequency from the voice of the first speaker X input via the microphone 33 as a frequency that can identify the native language of the speaker X. More specifically, the lowest 0th formant frequency (also referred to as the first formant frequency or the base frequency) of the formant frequencies is detected. For example, the first detection unit 41 extracts a peak by peak picking after linear predictive analysis (LPC), and detects the presence or absence of a peak for each band shown in FIG. Thereby, the presence or absence of the formant frequency is detected for each band, and the detection result is output to the first calculation unit 43 or the control unit 31. A known method can be widely applied as a formant frequency detection method.

FIG. 2 is a diagram illustrating an example of a relationship between a plurality of types of languages and the 0th formant frequency of a person who speaks each language as a mother tongue (speaker of native language). In FIG. 2, the frequency band from 0 to 15 kHz corresponding to the voice band is divided into nine bands, and the band of the 0th formant frequency is shown in a dark part for each language.
FIG. 2 shows an example of an adult. As shown in this figure, those whose native language is Japanese have a relatively low range of 0th formant frequency, and those whose native language is English or Italian tend to have a relatively high range of 0th formant frequency. There is.

  Thus, there is a correlation between the language and the 0th formant frequency. For this reason, for example, when a person whose mother tongue is Japanese speaks English, the 0th formant frequency of the English voice is in a low range (0 to 1.25 kHz in FIG. 2) which is a Japanese frequency band. Easy to be. In addition, when a person whose native language is British English speaks Japanese, the 0th formant frequency of Japanese speech tends to be in a high range (2 kHz to 15 kHz in FIG. 2), which is the frequency band of British English. .

In this configuration, using this correlation (the 0th formant frequency is influenced by the native language), the first calculation unit 43 controls the 0th of the voice of the first speaker X under the control of the control unit 31. The first speaker X is determined from the formant frequency, and the first speaker X is a native speaker (corresponding to the first speaker) or a language learner (corresponding to the second speaker) based on the determination result. A first determination process is performed to determine whether or not.
The storage unit 32 stores language-specific frequency information 32A that associates a plurality of types of languages with formant frequencies of persons whose mother tongue is each language based on the tendency shown in FIG. By using the frequency information 32A, the native language can be easily specified from the 0th formant frequency.

The mobile phone 23 is a user-fixed device because it is assumed that the first speaker X always uses it. For this reason, the setting language 23A of the mobile phone 23 is often set to the native language.
On the other hand, the setting language 27A of the in-vehicle device 27 is not necessarily set to the native language. This is because if the actual road sign is other than the native language and the setting language 27A of the in-vehicle device 27 is set to the native language, the characters of the actual road sign cannot be accurately recognized on the in-vehicle device 27 side, and navigation processing and map This is because there is a risk of deficiencies in the display of the above. For this reason, the setting language 27A of the in-vehicle device 27 is often set to the language of the actual road sign.
Therefore, in this configuration, in order to further improve the native language determination accuracy, the first calculation unit 43 is a user of the mobile phone 23 under the control of the control unit 31 based on at least the set language 23A of the mobile phone 23. A second determination process is performed in which the native language of the first speaker X is specified, and whether the first speaker X is a native speaker or a language learner is determined based on the specified result.

In addition, it is considered that there are relatively many calls between native speakers and language learners after calls between native speakers. When a native speaker speaks, the number of times a sentence is interrupted for a long time is small. However, in the case of a language learner, the speech is uttered while considering words and grammar.
Therefore, in this configuration, in order to further improve the native language determination accuracy, the first calculation unit 43 acquires information on the silent part of the voice of the first speaker X under the control of the control unit 31, and the acquired information Based on the above, a third determination process is performed to determine whether the first speaker X is a native speaker or a language learner.

The echo canceller 45 performs echo cancellation processing on the audio signal from the microphone 33, thereby canceling the echo generated by spreading the sound emitted from the speaker 35 with the microphone 33.
In addition, when the second speaker Y is a language learner, the control unit 31 performs predetermined sound processing for the language learner on the sound signal input from the microphone 33 (corresponding to the transmitted speech signal). Specifically, the control unit 31 performs a process of slow reproduction of sound (corresponding to a process of reducing the reproduction speed) as the predetermined sound process. That is, a sampling rate converter (hereinafter referred to as SRC 47) is arranged between the microphone 33 and the first calculation unit 43, and the control unit 31 multiplies the sampling frequency for the audio signal input from the microphone 33 by n times, In addition, the sampled data is thinned out appropriately to convert it into an audio signal that is played back slowly.

This audio signal is transmitted to the other telephone terminal 25 via the communication module 22, and the audio that is slowly reproduced from the other telephone terminal 25 is emitted. Note that, by setting the sampling frequency and the like to default values, sound is emitted from other telephone terminals 25 at an actual speed.
In this way, the SRC 47 functions as a first slow playback unit that performs audio processing for slow playback. In this case, it is preferable to suppress the uncomfortable feeling on the listening side (second speaker Y side) by slowing down the playback speed in steps. Note that the slow playback configuration is not limited to the SRC 47. Further, the predetermined voice processing for language learners does not have to be limited to slow reproduction, and voice processing that is easy for language learners to hear (corresponding to voice processing for language learners) is widely applicable.

In the call device 21, the second detection unit 51 can specify the native language of the speaker Y from the voice of the second speaker Y input via the communication module 22 (corresponding to the received voice during a hands-free call). A formant frequency (the 0th formant frequency in the present configuration) is detected as a low frequency. The same thing as the 1st detection part 41 is applicable to this 2nd detection part 51. FIG.
Under the control of the control unit 31, the second calculation unit 53 determines the mother tongue of the second speaker Y from the 0th formant frequency of the voice of the second speaker Y, and based on the determination result, the second speaker Y First determination processing is performed to determine whether the speaker is a native speaker (corresponding to the first speaker) or a language learner (corresponding to the second speaker).
Further, in order to further improve the native language determination accuracy, the second calculation unit 53 acquires information on the silent part of the voice of the second speaker Y under the control of the control unit 31, and based on the acquired information, A third determination process is performed to determine whether the speaker Y is a native speaker or a language learner.

By the way, the 1st calculating part 43 determines the native language of the 1st speaker X based on the setting language 23A of the mobile telephone 23 which the 1st speaker X uses, and the 1st speaker X is a native language based on the determination result. The second determination process is performed to determine whether the speaker is a language learner or not, but the telephone device 21 does not know the language set for the other telephone terminal 25 used by the second speaker Y. In the second calculation unit 53, the second determination process is not executed.
However, when the setting language of the other telephone terminal 25 used by the second speaker Y is known by communication between the telephone apparatus 21 and the other telephone terminal 25, the side of the telephone apparatus 21 (second arithmetic unit) 53), a second determination process may be performed for determining whether the second speaker Y is a native speaker or a language learner based on the set language.
Note that the control unit 31 may perform the second and third determination processes described above.

When the first speaker X is a language learner, the control unit 31 performs predetermined sound processing for the language learner on the sound signal of the second speaker Y input via the communication module 22. This predetermined sound processing is processing for slow reproduction of sound.
That is, a sampling rate converter (hereinafter referred to as SRC 57) is connected to the communication module 22, and the control unit 31 uses the SRC 57 in the same manner as described above to slowly reproduce the voice signal of the second speaker Y. Is selectively converted into an audio signal. Also in this case, it is preferable that the slow-played audio signal suppresses a sense of discomfort on the listening side (first speaker X side) by gradually reducing the playback speed. In FIG. 1, reference numeral 58 denotes a low-pass filter (LPF) disposed on the output side of the SRC 57.
Note that the slow playback configuration is not limited to the SRC 57. Moreover, the predetermined audio processing for language learners is not limited to the audio processing for slow reproduction, and audio processing for language learners can be widely applied.

FIG. 3 is a flowchart showing the operation of the communication device 21 for the vehicle-side speaker (first speaker X).
When the first detection unit 41 detects that the utterance voice is input to the microphone 33 (step S1A), the call device 21 uses the first calculation unit 43 to perform the first determination process (step S2A) described above, A second determination process (step S3A) and a third determination process (step S4A) are executed.
In the first determination process, the first calculation unit 43 specifies the 0th formant frequency of the voice of the first speaker X, and then refers to the frequency-specific frequency information 32A stored in the storage unit 32 to thereby change the first formant frequency. Identify the native language of speaker X. Next, it is determined from the identified native language whether the first speaker X is a native language speaker or a language learner.

  Various methods can be applied to the method of determining whether the speaker is a native speaker or a language learner from the native language. For example, if the native language is the same language as the official language of the country in which the call device 21 is used, the first speaker X is determined as the native speaker, and the language is determined as a language learner in another language. May be. Further, the speech recognition technology is applied to identify the language of the first speaker X, and when the native language is the same as the identified language, the first speaker X is determined to be a native speaker, In some cases, a method of determining a language learner may be applied.

  In the second determination process, the first calculation unit 43 compares the set languages 23A and 27A of the mobile phone 23 and the in-vehicle device 27 to identify the native language, and whether the first speaker X is the native speaker from the identified native language. Determine if you are a language learner. When the set languages 23A and 27A match, the language is specified as a native language, and when they do not match, the set language 23A of the mobile phone 23 is specified as the native language. Further, when the setting language 27A of the in-vehicle device 27 cannot be specified, the setting language 23A of the mobile phone 23 may be specified as the native language. In addition, the method for determining whether the speaker is a native speaker or a language learner from the identified native language may be the same determination method as the first determination process or a different determination method.

In the third determination process, the first calculation unit 43 counts the number of silent portions from the voice of the first speaker X input via the microphone 33, and the first speaker X is the mother tongue based on the count result. Determine if you are a speaker or a language learner. There are a plurality of methods for this determination method. For example, it may be determined that the language learner is determined when the number of silent portions is greater than a predetermined threshold value within a predetermined time, and the speaker is determined as a native speaker when the number is small.
In addition, the number of silent parts of the voice of the first speaker X and the voice of the second speaker Y input via the communication module 22 are considered in view of the relatively large number of calls between the native speaker and the language learner. A method may be used in which the number of silent portions is compared and the language learner is determined as having a higher number of times.

The first calculation unit 43 acquires the respective determination results by performing the first to third determination processes in parallel, and then, based on these determination results, the first speaker X is a native speaker or a language learner. Whether or not (step S5A). The process from step S2A to S5A corresponds to a determination step.
When the determination results of the first to third determination processes are different, priority is given to a determination result having a high priority. In this configuration, the first determination result is given the highest priority. When the first determination result cannot be obtained (for example, including the case of the 0th formant frequency included in a plurality of native languages such as 1 kHz to 1.5 kHz in FIG. 2), the second and third determinations are made. By using the processing determination result, it becomes easy to specify one native language. The priority order may be changed.

When it is determined in step S5A that the first speaker X is a native speaker (that is, not a language learner) (step S5A; NO), the call device 21 causes the control unit 31 to execute the process (on the vehicle side). The operation of the speaker (corresponding to the operation for the first speaker X) is terminated.
On the other hand, when it is determined in step S5A that the first speaker X is a language learner (step S5A; NO), the call device 21 uses the SRC 57 to determine the second speaker Y that is the received voice. The audio signal is played slowly (step S6A, corresponding to the audio processing step). Thereby, the first speaker X determined to be a language learner can hear the voice of the second speaker Y slowly and can easily hear the voice.

  Note that the processing from step S1A to S5A is completed in a short time of about several seconds, and the slow reproduction is started in a short time. If it is determined that the first speaker X is a native speaker (that is, not a language learner), the process of step S6A is not executed. The voice of the two speaker Y can be heard at the actual speed.

FIG. 4 is a flowchart showing the operation of the communication device 21 for a speaker outside the vehicle (second speaker Y).
When the second detecting unit 51 detects that the received voice (the voice of the second speaker Y) is input from the mobile phone 23 via the communication module 22 (step S1B), the call device 21 detects the second calculating unit. 53, the first determination process (step S2B) and the third determination process (step S4B) described above are executed.
In this first determination process, the second calculation unit 53 specifies the 0th formant frequency of the voice of the second speaker Y, and then refers to the language-specific frequency information 32A stored in the storage unit 32. The native language of the second speaker Y is specified. Next, it is determined from the identified native language whether the second speaker Y is a native language speaker or a language learner. The first determination process is the same as the first determination process executed by the first calculation unit 43 except that the voice of the second speaker Y is used.

  In the third determination process, the first calculation unit 43 counts the number of silent portions from the voice of the second speaker Y, and whether the second speaker Y is a native speaker or a language learner based on the counting result. Determine whether or not. The third determination process is the same as the third determination process executed by the first calculation unit 43 except that the voice of the second speaker Y is used.

The first calculation unit 43 performs the first and third determination processes in parallel, and acquires the respective determination results. Then, based on these determination results, the second speaker Y is a native speaker or a language learner. Whether or not (step S5B). The process from step S2B to S5B corresponds to a determination step.
When the determination results of the first and third determination processes are different, priority is given to a determination result having a high priority. In this configuration, the first determination result is given the highest priority. The priority order may be changed.

When it is determined in step S5B that the second speaker Y is a native speaker (that is, not a language learner) (step S5B; NO), the call device 21 causes the control unit 31 to perform the process (outside the vehicle). The speaker (corresponding to the operation for the second speaker Y) is terminated.
On the other hand, when it is determined in step S5B that the second speaker Y is a language learner (step S5B; YES), the call device 21 uses the SRC 47 to transmit the first speaker X that is the transmitted voice. Are reproduced in a slow manner (step S6B, corresponding to the audio processing step). Thereby, the second speaker Y determined to be a language learner can hear the voice of the first speaker X slowly and easily hear the voice. Note that the processing from step S1B to S5B is completed in a short time of about several seconds, and the slow playback is started in a short time.

If it is determined that the second speaker Y is a native speaker (that is, not a language learner), the process of step S6B is not executed. The voice of the speaker X can be heard at the actual speed.
Further, in the flowchart shown in FIG. 4, the process of step S4B (third determination process) may be omitted.

As described above, in the present embodiment, the first speaker X, the first calculation unit 43, and the control unit 31 make the first speaker X a native speaker based on at least the voice of the first speaker X. The determination part which determines whether it is a language learner is comprised.
Moreover, with respect to the voice signal (the voice of the second speaker Y) output by the control unit 31 and the SRC 57 toward the first speaker X determined to be a language learner based on the determination result of the determination unit. A sound processing unit that performs slow reproduction processing (corresponding to predetermined sound processing for language learners) is configured.
This automatically identifies whether the first speaker X is a native speaker or a language learner without using a manual switch or the like, and even if the first speaker X is a language learner. It becomes easy to talk with the two speaker Y.

In addition, the second detection unit 51, the second calculation unit 53, and the control unit 31 determine whether the second speaker Y is a native speaker or a language learner based on at least the voice of the second speaker Y. A determination unit is configured.
Moreover, with respect to the voice signal (the voice of the first speaker X) output by the control unit 31 and the SRC 47 toward the second speaker Y determined to be a language learner based on the determination result of the determination unit. A sound processing unit that performs slow reproduction processing (corresponding to predetermined sound processing for language learners) is configured.
This automatically identifies whether the second speaker Y is a native speaker or a language learner without using a manual switch or the like, and even if the second speaker Y is a language learner. It becomes easier to talk to the speaker X.

In the present embodiment, the native speaker may not be limited to a native speaker with a strict meaning, but may include a person who speaks similar to the native speaker. Further, the language learner does not have to be limited to a language learner having a strict meaning, and may include a person who speaks similar to the language learner.
For example, in the case of an elderly person, even if it is a native speaker, there may be many silent sections, and in this case, it may be determined as a language learner in the third determination process. Further, depending on individual differences, even a native speaker may be determined as a language learner in the first determination process or the like. In any case, the range determined to be a native speaker or a language learner can be adjusted by appropriately adjusting the determination criteria.
That is, in the first to third determination processes, it may be determined whether the first speaker corresponding to the native speaker or the second speaker corresponding to the language learner.

  In addition, as a method for determining whether the speaker is the first speaker or the second speaker, the first determination process is performed. That is, each speech is determined from the voices of the first speaker X and the second speaker Y. The 0th formant frequency, which is predetermined frequency information that can identify the native language of the person X, Y, is acquired, the native language is specified based on the acquired 0th formant frequency, and the first speaker is used using the specified native language Therefore, it is possible to specify the native language of each speaker X and Y with high accuracy using the correlation between the language and the 0th formant frequency.

  In the first determination process, the case where the 0th formant frequency is used has been described. However, the first formant frequency may not be limited to the 0th formant frequency. For example, if the native language of the speakers X and Y can be identified from formant frequencies other than the 0th formant frequency, the formant frequency may be used. In addition to the formant frequency, if there is frequency information that can identify the native language of the speakers X and Y, the frequency information may be used.

  Further, in the present embodiment, language-specific frequency information 32A that associates plural types of languages with formant frequencies of persons whose mother tongue is each language is stored, and the mother language is specified based on the language-specific frequency information 32A. It is easy to identify the mother tongue.

  In the present embodiment, since the second determination process is performed, that is, by using the setting language 23A set in the mobile phone 23 which is a user-fixed device used by the call device 21 for a call, the mobile phone Since it is determined whether the first speaker X that can be regarded as 23 users is the first speaker or the second speaker, it is determined whether the first speaker X is the first speaker or the second speaker. It becomes easy to improve the determination accuracy.

  Furthermore, in the second determination process, when the setting language 23A of the mobile phone 23 matches the setting language 27A of the in-vehicle device 27 connected to the call device 21, the language is identified as the native language and does not match. Specifies the set language 23A of the mobile phone 23 as a native language, and determines whether the first speaker X is the first speaker or the second speaker using the identified native language. Thereby, it becomes easy to improve the determination accuracy of whether it is a 1st speaker or a 2nd speaker. In addition, since this 2nd determination process is performed only about the 1st speaker X, the 1st speaker X becomes easier to improve determination accuracy than the 2nd speaker Y.

In the present embodiment, since the third determination process is performed, that is, from the voices of the first speaker X and the second speaker Y, information on the silent part of the voices of the speakers X and Y is acquired. Since it is determined whether each speaker X, Y is the first speaker or the second speaker based on the acquired information, whether each speaker X, Y is the first speaker or the second speaker is determined. It becomes easier to improve the determination accuracy.
In addition, when the determination results of the first to third determination processes are different, it is determined whether the speaker is the first speaker or the second speaker according to a predetermined priority. It becomes easy.

In addition, the communication device 21 includes a microphone 33 that functions as a sound collecting unit that collects the voice of the first speaker X among the plurality of speakers X and Y, and the first speaker X (corresponding to a predetermined speaker). ) And a speaker 35 that functions as a sound emitting unit that emits the voice of the second speaker Y. When the first speaker X is determined to be a second speaker corresponding to a language learner, a slow reproduction process (predetermined for language learners) is applied to an audio signal corresponding to the sound emitted by the speaker 35. Equivalent to voice processing). This makes it easier for the first speaker X who uses the microphone 33 and the speaker 35 to hear the call.
When the microphone 33 and the speaker 35 are separate, the call device 21 includes a sound input unit that inputs sound from the microphone 33 as a sound collecting unit, and outputs sound toward the speaker 35 as a sound emitting unit. An audio output unit may be provided.

Further, since the communication device 21 is a hands-free communication device used by the first speaker X for hands-free communication, the first speaker X who is a direct user of the communication device 21 can easily hear the call.
It is determined whether the first speaker X and the second speaker Y are the first speaker or the second speaker, and each speaker X, Y is the second speaker. However, the present invention is not limited to this, and it is determined whether only one (for example, the first speaker X) is the first speaker or the second speaker. However, when the speaker is the second speaker, the other speaker may make it easy to hear the call.

(Second embodiment)
FIG. 5 is a flowchart for explaining the operation of the call device 21 according to the second embodiment, and shows the operation of the call device 21 for a speaker outside the vehicle (second speaker Y).
In the second embodiment, the storage unit 32 of the call device 21 stores the telephone number of the call partner (second speaker Y) determined to be a language learner, and the phone number of the call partner is stored in the storage unit. 32 is different from the first embodiment in that the process proceeds to step S6A without performing the determination process.
Hereinafter, the description which overlaps with 1st embodiment is abbreviate | omitted.

As shown in FIG. 5, when the received voice (second speaker Y's voice) is input from the mobile phone 23 (step S1B), the telephone device 21 receives the telephone number of the second speaker Y who is the other party. Then, it is determined whether or not the language learner's telephone number is stored in the storage unit 32 (step S11B).
Note that the telephone number can be acquired by acquiring the telephone number used for the outgoing call when making a call from the telephone device 21 (mobile phone 23). What is necessary is just to acquire the telephone number notified from the telephone terminal 25 via a telephone network.

  Here, in the call device 21, when the call with the second speaker Y who is the call partner is the first time or when the call with the same second speaker Y is in the past, the second speaker Y is the native speaker. If it is determined that the telephone number of the second speaker Y is not stored in the storage unit 32. For this reason, the determination in step S11B is a negative result (step S11B; NO), and the process proceeds to the next step S2B.

Thereafter, when it is determined in step S5B that the second speaker Y is a language learner (step S5B; YES), the call device 21 performs slow playback of the voice signal of the first speaker X (step S6B). The telephone number of the second speaker Y is stored in the storage unit 32 as the telephone number of the language learner (step S12B).
For this reason, after that, when talking with the same second speaker Y, the determination in step S11B is affirmative (step S11B; YES), and the process proceeds to step S6B as shown in FIG. As a result, the first and third determination processes (corresponding to the determination step) can be omitted, and the start of the slow playback in step S6B can be accelerated.

  If the same telephone number has already been stored in the storage unit 32 in step S12B, the telephone number is not newly stored. This avoids a situation where the same telephone number is double registered in the storage unit 32.

  As described above, in the present embodiment, the storage unit 32 stores the telephone number of the second speaker Y determined as the language learner (second speaker), and at the start of the call, the second speaker Y Is stored in the storage unit 32, the first speaker X's audio signal is played slowly without performing the first and third determination processes. Thereby, it is possible to promptly perform slow reproduction.

The above-described embodiments are merely illustrative of one embodiment of the present invention, and can be arbitrarily modified and applied without departing from the spirit of the present invention.
For example, although the case where this invention is applied to the telephone apparatus 21 shown in FIG. 1 and its control method was demonstrated, it is not limited to this. For example, the present invention may be applied to a communication device that is not limited to a vehicle and a control method thereof. Further, the present invention is not limited to the call device 21 that makes a one-to-one call, and the present invention may be applied to a call device that allows three or more people to call, such as the conference support device described in Patent Document 1.

  In the above-described embodiment, the case where the control program is stored in the storage unit 32 in advance has been described. However, the control program can be recorded on a computer-readable recording medium such as a magnetic recording medium, an optical recording medium, or a semiconductor recording medium. The program may be stored in a medium, and the computer may read the control program from the recording medium and execute it. Further, the control program may be downloaded from a distribution server or the like on a communication network via an electric communication line.

DESCRIPTION OF SYMBOLS 10 Call system 21 Call apparatus 22 Communication module 23 Mobile phone 23A, 27A Setting language 25 Other telephone terminals 27 In-vehicle apparatus 31 Control part (determination part, voice processing part)
32 Storage Unit 32A Frequency Information by Language 33 Microphone (Sound Collection Unit)
35 Speaker (sound emission part)
41 1st detection part (determination part)
43 First operation unit (determination unit)
45 Echo canceller 47, 57 SRC (voice processing unit)
51 2nd detection part (determination part)
53 Second operation unit (determination unit)
58 Low-pass filter (LPF)
X First speaker Y Second speaker

Claims (11)

In a call device that inputs and outputs audio signals corresponding to each speaker's voice so that multiple speakers can talk to each other,
A determination unit for determining whether the speaker is a first speaker equivalent to a native speaker or a second speaker equivalent to a language learner based on at least the voice of the speaker;
A voice processing unit that performs predetermined voice processing for a language learner on a voice signal output toward a speaker determined to be the second speaker based on the determination result of the determination unit;
A call device comprising:   The determination unit acquires predetermined frequency information capable of specifying the speaker's native language from the speaker's voice, specifies a native language based on the acquired frequency information, and uses the identified native language to determine the first language. The call device according to claim 1, wherein a first determination process is performed to determine whether the speaker is the first speaker or the second speaker. The predetermined frequency information is a 0th formant frequency,
3. The determination unit according to claim 2, wherein the determination unit specifies a native language based on language-specific frequency information in which a plurality of types of languages are associated with a 0th formant frequency of a person whose native language is each language. Telephone device.   Whether the speaker that can be regarded as the user of the user-fixed device using the language set in the user-fixed device used by the call device for the call is the first speaker or the second speaker The call device according to claim 2, wherein a second determination process is performed to determine whether or not.   In the second determination process, if the language set in the user-fixed device matches the language set in the in-vehicle device connected to the call device, the language is identified as the native language and does not match The language set in the user-fixed device is specified as a native language, and the identified native language is used to determine whether the first speaker or the second speaker is used. 4. The communication device according to 4.   The determination unit acquires information on a silent portion of the voice from the voice of the speaker, and determines whether the first speaker or the second speaker is based on the acquired information. 6. The call device according to claim 4, wherein a determination process is performed.   7. The method according to claim 6, wherein when the determination results of the first to third determination processes are different, it is determined whether the first speaker or the second speaker according to a predetermined priority. Telephone device. The call device includes: a sound collection unit that collects voices of a predetermined speaker among the plurality of speakers; and a sound emission unit that emits voices of other speakers toward the predetermined speaker And
When the predetermined speaker is determined to be the second speaker, the voice processing unit generates a predetermined voice signal for a language learner in a voice signal corresponding to the voice to be emitted by the sound emitting unit. The call device according to any one of claims 1 to 7, wherein voice processing is performed.   9. The call device according to claim 8, wherein the call device is a hands-free call device used by the predetermined speaker for a hands-free call. A storage unit for storing a telephone number of the other speaker determined to be the second speaker;
When the telephone number of the other speaker has already been stored in the storage unit at the start of the call, the voice processing unit outputs the voice to the other speaker without making the determination The call device according to claim 8 or 9, wherein predetermined speech processing for language learners is performed on the signal. In a control method of a call device that inputs and outputs audio signals corresponding to each speaker's voice so that a plurality of speakers can talk to each other,
A determination step of determining whether the speaker is a first speaker equivalent to a native speaker or a second speaker equivalent to a language learner based on at least the voice of the speaker;
An audio processing step for performing predetermined audio processing for a language learner on an audio signal output toward the speaker determined to be the second speaker based on the determination result of the determination step;
A method for controlling a communication device, characterized in that:

Images