JP2010166324A - Portable terminal, voice synthesizing method, and program for voice synthesis - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To switch to voice synthesis based on a specific keyword, to perform filtering to a raw voice and to automatically register the specific keyword in a portable terminal capable of performing a voice communication. <P>SOLUTION: The portable terminal has a voice analyzing means and a voice converting means at the previous stage of a voice synthesizing means. The voice synthesizing means converts a received voice into a synthesized voice that imitates a particular person, such as a talent. It is determined whether a transmission source of the received voice is a switching partner of voice synthesis. The voice feeling of a reception voice is analyzed. When the converting means recognizes a voice of a specific keyword preregistered in a keyword database, the converting means stops the voice synthesis and outputs a voice with the reception voice as it is. When the keyword is registered as an NG word, a determined NG word is notified to the partner. When a result that the voice feeling of the received voice is a specific feeling such as anger is obtained, the voice synthesis is stopped, processing that outputs a voice obtained by filtering the original voice is performed. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a mobile terminal, and more particularly to a mobile terminal that outputs sound.

  Currently, in the profits of mobile phone carriers (carriers), the ratio of data packets is increasing and the ratio of voice is decreasing.

  Accordingly, mobile phone operator companies are aiming to increase the profitability of voice along with the expansion of market share by providing mobile terminals and services with unique applications (application software).

  However, even if a conventional mobile phone has a speech synthesis function, it is impossible to switch speech synthesis based on a specific keyword, filter to raw speech, and automatically register a specific keyword.

  As a related technique, a voice quality conversion method and apparatus are disclosed in Japanese Patent Laid-Open No. 10-097267 (Patent Document 1). In this related technology, the voice quality of the input voice is converted using an analysis / synthesis method so that the voice quality is converted in a direction that matches the user's (user) preference, and voices with different voice quality are synthesized. It is intended to output good speech, synthesized speech of desired sound quality, and synthesized speech of various voice qualities.

Japanese Patent Laid-Open No. 10-097267

  An object of the present invention is to provide a portable terminal that analyzes voice and performs synthesis and conversion.

  The portable terminal of the present invention includes a voice analysis unit, a conversion unit, and a voice synthesis unit. The voice analysis means determines whether the identification information of the other party of voice communication is registered as a voice synthesis target. If the identification information is registered as a voice synthesis target, the voice analysis unit analyzes a spectrum of the voice signal related to voice communication, It is determined whether or not the voice based on the voice corresponds to a voice pattern indicating a specific emotion. When the voice is a voice corresponding to the voice pattern, the conversion means performs a filtering process for filtering the voice and outputs the filtered voice. In addition, when the voice is not a voice corresponding to the voice pattern, the conversion unit determines whether the keyword included in the voice signal corresponds to the NG word, and when the keyword corresponds to the NG word, Notify that the keyword is an NG word. The voice synthesizer synthesizes a predetermined voice with the voice based on the voice signal and outputs a synthesized voice. Note that examples of voice communication include telephone calls, reception of television broadcasts and radio broadcasts, reception of streaming data, acquisition and reproduction of voice data from a storage device, and the like. The source of the audio signal indicates the other party of the transmission source when the audio signal is an externally received signal, and indicates the user of the portable terminal when the audio signal is an externally transmitted signal. However, actually, it is not limited to these examples.

  In the speech synthesis method of the present invention, it is determined whether or not the identification information of the speech communication partner is registered as a speech synthesis target. When the identification information is registered as a speech synthesis target, the spectrum of the speech signal related to speech communication is analyzed to determine whether the speech based on the speech signal is a speech that corresponds to a speech pattern indicating a specific emotion. Further, when the voice is a voice corresponding to the voice pattern, a filtering process for filtering the voice is performed, and the filtered voice is output. If the voice is not a voice corresponding to the voice pattern, it is determined whether the keyword included in the voice signal corresponds to the NG word. If the keyword corresponds to the NG word, the keyword is determined to be NG word for the source of the voice signal. Notify that. Further, a predetermined voice is synthesized with the voice based on the voice signal, and a synthesized sound is output.

  The speech synthesis program according to the present invention includes a step of determining whether identification information of a speech communication partner is registered as a speech synthesis target, and a spectrum of a speech signal related to speech communication when the identification information is registered as a speech synthesis target. And determining whether the voice based on the voice signal is a voice corresponding to a voice pattern indicating a specific emotion, and if the voice is a voice corresponding to the voice pattern, a filtering process for filtering the voice is performed. And outputting a filtered voice and if the voice is not a voice corresponding to a voice pattern, determine whether the keyword included in the voice signal corresponds to a NG word, and if the keyword corresponds to a NG word, Informing the source of the audio signal that the keyword is an NG word; For voice-based No. performs synthesis of a given voice, a program for executing the steps on a computer for outputting the synthesized sound.

  Improve the utility value of voice communication functions such as telephone functions.

It is a block diagram which shows the structural example of the portable terminal in 1st and 2nd embodiment of this invention. It is a flowchart which shows operation | movement of the portable terminal in 1st Embodiment of this invention. It is a flowchart which shows operation | movement of the portable terminal in 2nd Embodiment of this invention. It is a block diagram which shows the structural example of the portable terminal in the 3rd and 4th embodiment of this invention. It is a flowchart which shows operation | movement of the portable terminal in 3rd Embodiment of this invention. It is a flowchart which shows operation | movement of the portable terminal in 4th Embodiment of this invention.

<First Embodiment>
Hereinafter, a first embodiment of the present invention will be described with reference to the accompanying drawings.
Referring to FIG. 1, the portable terminal of the present invention includes an antenna unit 11, a receiving unit 12, a voice analysis function unit 13, a conversion function unit 14, a voice synthesis function unit 15, a voice output unit 16, and a voice. An input unit 17, a transmission unit 18, a telephone number book 21, a keyword database 22, and a voice database 23 are provided.

  Here, a mobile phone is assumed as an example of the mobile terminal. However, in practice, the portable terminal is a PC (personal computer), a mobile notebook PC, a thin client terminal, a car navigation system (car navigation system), a portable music player, a portable game machine, a home game machine, an interactive TV, a digital tuner, Digital recorders, information home appliances, OA (Office Automation) devices, and the like may be used. Essentially, the portable terminal of the present invention may be any electronic device that can output sound.

  The antenna unit 11 transmits and receives signals by radio waves. Here, wireless communication is assumed as the communication method of the mobile terminal, but actually, wired communication may be used.

  The receiving unit 12 converts an external signal received by the antenna unit 11 into an audio signal. Here, the receiving unit 12 demodulates and converts the high-frequency signal received by the antenna unit 11 into a baseband signal. Note that the baseband signal indicates a signal before modulation and an information signal after demodulation (audio, video, digital data, etc.) in a system that performs modulation and demodulation. Here, the baseband signal is an audio signal.

  The voice analysis function unit 13 determines whether identification information such as the telephone number of the other party who made the call is registered in the telephone number book 21 as a voice synthesis target number. In addition, the voice analysis function unit 13 analyzes the spectrum of the voice signal and determines whether or not the voice based on the voice signal is a voice indicating a specific emotion such as anger. For example, the voice analysis function unit 13 refers to a voice pattern indicating a specific emotion stored outside or inside the mobile terminal, and whether the voice pattern based on the voice signal matches the voice pattern indicating the specific emotion. Judging. However, actually, it is not limited to these examples. Thereafter, the voice analysis function unit 13 sends a voice signal to the conversion function unit 14. At this time, if the voice based on the voice signal indicates a specific emotion such as anger, the voice analysis function unit 13 indicates that the voice indicates a specific emotion, or filters the original voice. Is sent to the conversion function unit 14. Note that the conversion function unit 14 unconditionally sends the audio signal to the conversion function unit 14 when it is not determined whether the audio based on the audio signal is an audio signal indicating a specific emotion such as anger.

  The conversion function unit 14 refers to the keyword database 22 and outputs keyword data indicating a specific keyword according to the voice signal analyzed by the voice analysis function unit 13. Here, when the keyword included in the voice signal from the other party who made the call is registered in the keyword database 22 as an NG word, the conversion function unit 14 sends the keyword to the other party via the transmission unit 18. A predetermined NG word or a notification that it is an NG word is transmitted. For example, when the keyword “XX” included in the audio signal is registered in the keyword database 22 as an NG word, the conversion function unit 14 sends “ NG word "is sent. Note that the conversion function unit 14 may convert the voice of the NG word portion into silence or beep sound when the keyword included in the voice signal is registered in the keyword database 22 as an NG word. Moreover, the conversion function part 14 will perform the process (filtering) which outputs the audio | voice which filtered the original audio | voice, if the audio | voice based on an audio | voice signal is an audio | voice which shows specific emotions, such as anger.

  The voice synthesis function unit 15 refers to the voice database 23 and synthesizes a predetermined voice according to the received voice signal. In the portable terminal of the present invention, the speech analysis function unit 13 and the conversion function unit 14 are arranged in the previous stage of the speech synthesis function unit 15.

  The audio output unit 16 performs audio output based on the received audio signal.

  The voice input unit 17 generates a voice signal based on voice input by a user or an application.

  The transmission unit 18 converts the audio signal and transmits the converted signal to the outside via the antenna unit 11. Here, the receiving unit 12 modulates a baseband signal that is an audio signal to convert it into a high-frequency signal, and transmits the high-frequency signal to the outside via the antenna unit 11.

  The telephone number book 21 stores identification information such as the telephone number of the other party who made the call. Here, the telephone number book 21 stores identification information such as the telephone number of the other party who is the target of speech synthesis among the other parties who have made a call. Note that the telephone number is merely an example, and in practice, it may be any identification information that can identify the other party who made the call. Moreover, the telephone number book 21 may be provided separately from the normal telephone number book which the portable terminal itself has.

  The keyword database 22 stores keyword data indicating specific keywords. Here, in the keyword database 22, sentences of specific conversations and NG words are registered. For registration of a specific keyword, when the receiving operator presses a button for operating the conversion function unit 14, the voice analysis function unit 13 analyzes the voice from when the button is pressed to a predetermined time before. A specific keyword is detected, and keyword data indicating the detected keyword is automatically registered in the keyword database 22. In this case, the voice analysis function unit 13 temporarily stores voices from when the button is pressed to a predetermined time before. Note that the conversion function unit 14 may download specific keyword data from a WEB site or the like and register it in the keyword database 22 in accordance with the operation of the operator. At this time, the conversion function unit 14 may download the keyword database 22 itself from a WEB site or the like.

  The voice database 23 stores predetermined voice data. Here, it is assumed that voice data similar to the voice of a specific person is stored in the voice database 23. As an example of a specific person, a talent (celebrity), other celebrities, a user's family, an acquaintance, etc. can be considered. However, actually, it is not limited to these examples. The voice synthesis function unit 15 downloads predetermined voice data from a WEB site or the like and registers it in the voice database 23 in accordance with the operation of the operator. At this time, the speech synthesis function unit 15 may download the speech database 23 itself from a WEB site or the like.

  Examples of communication lines used by the antenna unit 11 include a mobile phone network, WiMAX, 3G (third generation mobile phone), the Internet, a LAN (Local Area Network), a wireless LAN (Wireless LAN), a cable television (CATV) line, A fixed telephone network, a leased line, IrDA (Infrared Data Association), Bluetooth (registered trademark), a serial communication line, and the like are conceivable. However, actually, it is not limited to these examples.

  Examples of the receiving unit 12 and the transmitting unit 18 include a network adapter such as a NIC (Network Interface Card), a communication port such as a connection port (connector), and the like. However, actually, it is not limited to these examples.

  As an example of the speech analysis function unit 13, the conversion function unit 14, and the speech synthesis function unit 15, a processing device such as a CPU (Central Processing Unit) or a microprocessor (microprocessor), or a semiconductor integrated circuit (Integrated Circuit) having a similar function (IC)) etc. are conceivable. Note that the speech analysis function unit 13, the conversion function unit 14, and the speech synthesis function unit 15 may be programs (speech recognition software, speech synthesis software, etc.) for causing a mobile terminal to execute each function. However, actually, it is not limited to these examples.

  Further, the conversion function unit 14 may cooperate with an input device for receiving an external input such as a user operation or an output device for performing a user notification. Examples of the input device include a keyboard, a keypad, a keypad on the screen, a touch panel, a tablet, and the like. Alternatively, the input device may be an interface (I / F) for acquiring information from an external input device or storage device. Examples of the output device include a display device such as an LCD (liquid crystal display), a PDP (plasma display), and an organic EL display (organic electroluminescence display), or a projection device such as a projector that projects display contents on a wall or a screen, A printing apparatus such as a printer that prints display contents on a sheet or the like can be considered. Alternatively, the output device may be an interface for outputting information to an external display device or storage device. However, actually, it is not limited to these examples.

  As an example of the audio output unit 16, a speaker, an earphone, a headphone, or the like can be considered. The audio output unit 16 may be integrated with a display device such as a display. However, actually, it is not limited to these examples.

  As an example of the voice input unit 17, a sound collector such as a microphone, character-speech conversion software, artificial voice software, an electronic musical instrument, and the like can be considered. The voice input unit 17 may be an interface (Interface (I / F)) for acquiring voice data stored in a storage device inside or outside the portable terminal. However, actually, it is not limited to these examples.

  As an example of the telephone number book 21, the keyword database 22, and the voice database 23, a semiconductor storage device such as a memory, an external storage device (storage) such as a hard disk, or a storage medium (media) can be considered. The telephone number book 21, the keyword database 22, and the voice database 23 are not limited to a storage device built in the main body of the mobile terminal, but are installed in a peripheral device (external HDD or the like) or an external server (storage server or the like). Or a NAS (Network Attached Storage). However, actually, it is not limited to these examples.

  With reference to FIG. 2, the operation of the portable terminal of the present invention will be described.

(1) Step S101
The antenna unit 11 receives a high-frequency signal when the other party makes a call.

(2) Step S102
The receiving unit 12 demodulates the received high-frequency signal, converts it to a baseband signal, and sends it to the voice analysis function unit 13. At this time, the receiving unit 12 sends to the voice analysis function unit 13 an information signal indicating the telephone number of the other party who made the call together with the baseband signal. Here, the baseband signal is an audio signal. The baseband signal may include digital data indicating the telephone number of the other party who made the call.

(3) Step S103
The voice analysis function unit 13 determines whether the telephone number of the other party who made the call is registered in the telephone number book 21 as a voice synthesis target number. Note that the telephone number is merely an example, and in practice, it may be any identification information that can identify the other party who made the call.

(4) Step S104
The voice analysis function unit 13 sends a voice signal directly to the voice output unit 16 when the telephone number of the other party who made the call is not a number registered in the telephone number book 21 as a voice synthesis target number. The audio output unit 16 performs audio output based on the audio signal. At this time, the voice analysis function unit 13 notifies the conversion function unit 14 and the voice synthesis function unit 15 not to operate, and then sends the voice output unit 16 via the conversion function unit 14 and the voice synthesis function unit 15. An audio signal may be sent.

(5) Step S105
The voice analysis function unit 13 recognizes that the voice synthesis is ON when the telephone number of the other party who made the call is a number registered as a voice synthesis target number in the telephone number book 21 and operates the conversion function unit 14. . For example, when the speech analysis function unit 13 recognizes that speech synthesis is ON, the speech analysis function unit 13 activates the conversion function unit 14 in the OFF state. Alternatively, the notification from the voice analysis function unit 13 to the conversion function unit 14 is changed from the prohibited state to the permitted state. That is, when the voice analysis function unit 13 recognizes that the voice synthesis is ON, the voice analysis function unit 13 can provide a voice signal to the conversion function unit 14 during a call with the other party.

(6) Step S106
The voice analysis function unit 13 analyzes the spectrum of the voice signal and determines whether or not the voice based on the voice signal is a voice indicating a specific emotion such as anger. Thereafter, the voice analysis function unit 13 sends a voice signal to the conversion function unit 14. At this time, if the voice based on the voice signal indicates a specific emotion such as anger, the voice analysis function unit 13 indicates that the voice indicates a specific emotion, or filters the original voice. Is sent to the conversion function unit 14. If the voice analysis function unit 13 does not determine whether the voice based on the voice signal is a voice indicating a specific emotion such as anger, the voice analysis function unit 13 sends the voice signal to the conversion function unit 14 unconditionally.

(7) Step S107
If the voice based on the voice signal indicates a specific emotion such as anger, the conversion function unit 14 performs processing (filtering) to output a voice obtained by filtering the original voice. Here, the conversion function unit 14 sends an audio signal after filtering the original audio to the audio output unit 16. The sound output unit 16 outputs sound obtained by filtering the original sound. At this time, the conversion function unit 14 sends a voice signal and a notification (filtering request) to filter the original voice to the voice synthesis function unit 15, and the voice synthesis function unit 15 filters the original voice. Alternatively, the voice synthesis function unit 15 may send the voice signal after filtering the original voice to the voice output unit 16.

(8) Step S108
If the voice based on the voice signal is not a voice indicating a specific emotion such as anger, the conversion function unit 14 refers to the keyword database 22 and adds a specific keyword to the voice signal analyzed by the voice analysis function unit 13. It is determined whether or not the indicated keyword data is included. At this time, if the voice signal analyzed by the voice analysis function unit 13 does not include keyword data indicating a specific keyword, the conversion function unit 14 sends the voice signal to the voice synthesis function unit 15.

(9) Step S109
When the speech signal analyzed by the speech analysis function unit 13 includes keyword data indicating a specific keyword, the conversion function unit 14 stops or prohibits speech synthesis for the speech synthesis function unit 15; A notification to output the original voice to the voice output unit 16 is sent. At this time, the voice synthesizing function unit 15 converts the voice corresponding to the specific keyword in the voice signal into silence or beep and sends it to the voice output unit 16, and outputs the other part as the original voice. Send to part 16. The audio output unit 16 performs audio output based on the audio signal.

(10) Step S110
When the voice signal analyzed by the voice analysis function unit 13 includes keyword data indicating a specific keyword, the conversion function unit 14 transmits a predetermined NG word based on the keyword data to the transmission unit 18. Output to. The transmitting unit 18 transmits a predetermined NG word to the other party who has made a call via the antenna unit 11. For example, based on the keyword data, the conversion function unit 14 notifies the calling party via the transmission unit 18 that the specific keyword is an NG word. At this time, the conversion function unit 14 may convert the sound of the NG word portion into silence or beep sound. Note that the conversion function unit 14 does not have to output the specific keyword to the transmission unit 18 when not notifying the other party who has made a call that the specific keyword is an NG word.

(11) Step S111
The speech synthesis function unit 15 refers to the speech database 23 and synthesizes speech similar to a specific person according to the received speech signal. Here, the speech synthesis function unit 15 synthesizes speech similar to a specific person with respect to the entire speech based on the received speech signal.

(12) Step S112
The voice synthesizing function unit 15 sends the synthesized voice signal to the voice output unit 16. The audio output unit 16 outputs a synthesized sound from a speaker or the like based on the synthesized audio signal.

(13) Step S113
The voice analysis function unit 13 continuously analyzes the emotion of the received voice until reception of the high-frequency signal is finished, and obtains a result that the voice based on the voice signal is a voice indicating a specific emotion such as anger. Then, the output of the current synthesized sound is stopped, and the process is switched to a process of outputting a sound obtained by filtering the original sound. The voice analysis function unit 13 ends the series of processes when the call is finished.

  The portable terminal of the present invention may be an audio reproduction device dedicated to reception, such as a portable music player compatible with television, radio, car navigation, and wireless communication. That is, the portable terminal of the present invention may not include the voice input unit 17 or the transmission unit 18. In this case, the portable terminal of the present invention does not notify the outside of NG words or the like.

  In the portable terminal of the present invention, if voice data of a specific person such as a talent is registered and placed in the voice database 23, the received voice can be heard with a synthesized sound imitating the specific person.

  The voice synthesis switching partner can be selected by registering the partner in the telephone number book 21 in advance or by registering the partner by pressing a switch even during a call. .

  When the voice of a specific keyword registered in advance in the keyword database 22 is recognized, the voice synthesis can be stopped and the voice as the received voice can be output.

  If the keyword is registered as an NG word, a predetermined NG word or a notification that it is an NG word can be output to the other party.

  Also, after analyzing the emotion of the received voice and finding that the voice based on the voice signal is a voice that expresses a specific emotion such as anger, the synthesized sound that imitates the voice of a specific person is stopped and the original voice is stopped. It is possible to perform a process of outputting a sound obtained by filtering the sound.

  The registration of a specific keyword can be automatically registered in the keyword database 22 by analyzing the voice of a predetermined time before the receiving operator presses the button.

  By using this mobile terminal, you can synthesize ringtones coming from a specific party into voices that look just like your favorite talent, creating an atmosphere as if you were talking to the talent.

  Also, by combining with the keyword database 22, it is possible to keep away the other party's emotions and NG words that you don't want to hear by speaking directly from the conversation.

  Here, voice conversion in a telephone (call) using a mobile terminal is described as an example. However, in reality, voice conversion when using a TV function, a radio function, or the like (during broadcast viewing), a storage device, Audio conversion when audio data stored in a storage medium or the like is reproduced (during audio reproduction) is also possible.

<Second Embodiment>
The second embodiment of the present invention will be described below.
In the first embodiment, when the speech signal analyzed by the speech analysis function unit 13 includes keyword data indicating a specific keyword, the conversion function unit 14 suspends or prohibits speech synthesis, and converts an NG word. In this embodiment, the speech synthesis is performed when the speech signal analyzed by the speech analysis function unit 13 includes keyword data indicating a specific keyword.

  The configuration of the mobile terminal in the present embodiment is basically the same as in the first embodiment. That is, the configuration of the mobile terminal in the present embodiment is as shown in FIG.

  With reference to FIG. 3, the operation of the mobile terminal in the present embodiment will be described.

(1) Step S201
The antenna unit 11 receives a high-frequency signal when the other party makes a call.

(2) Step S202
The receiving unit 12 demodulates the received high-frequency signal, converts it to a baseband signal, and sends it to the voice analysis function unit 13. At this time, the receiving unit 12 sends to the voice analysis function unit 13 an information signal indicating the telephone number of the other party who made the call together with the baseband signal. Here, the baseband signal is an audio signal. The baseband signal may include digital data indicating the telephone number of the other party who made the call.

(3) Step S203
The voice analysis function unit 13 determines whether or not the telephone number of the other party who made the call is registered in the telephone number book 21 as a voice synthesis target number. Note that the telephone number is merely an example, and in practice, it may be any identification information that can identify the other party who made the call.

(4) Step S204
The voice analysis function unit 13 sends a voice signal directly to the voice output unit 16 when the telephone number of the other party who made the call is not a number registered in the telephone number book 21 as a voice synthesis target number. The audio output unit 16 performs audio output based on the audio signal. At this time, the voice analysis function unit 13 notifies the conversion function unit 14 and the voice synthesis function unit 15 not to operate, and then sends the voice output unit 16 via the conversion function unit 14 and the voice synthesis function unit 15. An audio signal may be sent.

(5) Step S205
The voice analysis function unit 13 recognizes that the voice synthesis is ON when the telephone number of the other party who made the call is a number registered as a voice synthesis target number in the telephone number book 21 and operates the conversion function unit 14. . For example, when the speech analysis function unit 13 recognizes that speech synthesis is ON, the speech analysis function unit 13 activates the conversion function unit 14 in the OFF state. Alternatively, the notification from the voice analysis function unit 13 to the conversion function unit 14 is changed from the prohibited state to the permitted state. That is, when the voice analysis function unit 13 recognizes that the voice synthesis is ON, the voice analysis function unit 13 can provide a voice signal to the conversion function unit 14 during a call with the other party.

(6) Step S206
The voice analysis function unit 13 analyzes the spectrum of the voice signal and determines whether or not the voice based on the voice signal is a voice indicating a specific emotion such as anger. Thereafter, the voice analysis function unit 13 sends a voice signal to the conversion function unit 14. At this time, if the voice based on the voice signal indicates a specific emotion such as anger, the voice analysis function unit 13 indicates that the voice indicates a specific emotion, or filters the original voice. Is sent to the conversion function unit 14. If the voice analysis function unit 13 does not determine whether the voice based on the voice signal is a voice indicating a specific emotion such as anger, the voice analysis function unit 13 sends the voice signal to the conversion function unit 14 unconditionally.

(7) Step S207
If the voice based on the voice signal indicates a specific emotion such as anger, the conversion function unit 14 performs processing (filtering) to output a voice obtained by filtering the original voice. Here, the conversion function unit 14 sends an audio signal after filtering the original audio to the audio output unit 16. The sound output unit 16 outputs sound obtained by filtering the original sound. At this time, the conversion function unit 14 sends a voice signal and a notification (filtering request) to filter the original voice to the voice synthesis function unit 15, and the voice synthesis function unit 15 filters the original voice. Alternatively, the voice synthesis function unit 15 may send the voice signal after filtering the original voice to the voice output unit 16.

(8) Step S208
If the voice based on the voice signal is not a voice indicating a specific emotion such as anger, the conversion function unit 14 refers to the keyword database 22 and adds a specific keyword to the voice signal analyzed by the voice analysis function unit 13. It is determined whether or not the indicated keyword data is included. At this time, if the speech signal analyzed by the speech analysis function unit 13 includes keyword data indicating a specific keyword, the conversion function unit 14 outputs the speech signal to the speech synthesis function unit 15. Note that the conversion function unit 14 may output only a portion corresponding to a specific keyword in the voice signal to the voice synthesis function unit 15 and output the other portion to the voice output unit 16. Further, the conversion function unit 14 may output the keyword data to the speech synthesis function unit 15.

(9) Step S209
If the speech signal analyzed by the speech analysis function unit 13 does not include keyword data indicating a specific keyword, the conversion function unit 14 stops or prohibits speech synthesis for the speech synthesis function unit 15; A notification to output the original voice to the voice output unit 16 is sent. The audio output unit 16 outputs the original audio based on the audio signal.

(10) Step S210
When the voice signal analyzed by the voice analysis function unit 13 includes keyword data indicating a specific keyword, the conversion function unit 14 outputs the specific keyword to the transmission unit 18 based on the keyword data. . The transmission unit 18 transmits a specific keyword to the other party who has made a call via the antenna unit 11. For example, the conversion function unit 14 notifies the other party who has made a call via the transmission unit 18 that voice synthesis is to be performed for a specific keyword based on the keyword data. Note that the conversion function unit 14 does not need to output the specific keyword to the transmission unit 18 when not notifying the other party who has made a call that speech synthesis is performed for the specific keyword.

(11) Step S211
The speech synthesis function unit 15 refers to the speech database 23 and synthesizes speech similar to a specific person according to the received speech signal. Here, the speech synthesis function unit 15 synthesizes speech similar to a specific person with respect to the entire speech based on the received speech signal. The voice synthesis function unit 15 receives the keyword data from the conversion function unit 14, and based on the keyword data, only the voice of the specific keyword included in the voice based on the received voice signal is used. You may make it perform a synthesis | combination. For example, if the keyword data indicates a prominent utterance of a specific person, the speech synthesis function unit 15, if the speech based on the received audio signal includes the same content as the prominent utterance, Only the part is synthesized with sound similar to a specific person.

(12) Step S212
The voice synthesizing function unit 15 sends the synthesized voice signal to the voice output unit 16. The audio output unit 16 outputs a synthesized sound from a speaker or the like based on the synthesized audio signal.

(13) Step S213
The voice analysis function unit 13 continuously analyzes the emotion of the received voice until reception of the high-frequency signal is finished, and obtains a result that the voice based on the voice signal is a voice indicating a specific emotion such as anger. Then, the output of the current synthesized sound is stopped, and the process is switched to a process of outputting a sound obtained by filtering the original sound. The voice analysis function unit 13 ends the series of processes when the call is finished.

  As a result, the portable terminal of the present invention reproduces the voice of the user (person) when the voice of the user's acquaintance or famous speech of a celebrity is used during a call or voice playback. I can do it. At this time, it is assumed that the voice data (sound source) of the voice color has been licensed by the person concerned. As a method of obtaining a license, payment of consideration can be considered. As a method for obtaining voice-colored voice data (sound source), recording from the person with permission and downloading from a predetermined website can be considered.

<Third Embodiment>
The third embodiment of the present invention will be described below.
In the present embodiment, contrary to the first embodiment, the voice input by the user of the mobile terminal is synthesized and the synthesized sound is transmitted to the outside.

  Referring to FIG. 4, the mobile terminal in the present embodiment includes an antenna unit 11, a receiving unit 12, a voice analysis function unit 13, a conversion function unit 14, a voice synthesis function unit 15, a voice output unit 16, A voice input unit 17, a transmission unit 18, a telephone number book 21, a keyword database 22, and a voice database 23 are provided.

  Antenna unit 11, receiving unit 12, speech analysis function unit 13, conversion function unit 14, speech synthesis function unit 15, speech output unit 16, speech input unit 17, transmission unit 18, telephone number book 21, keyword database 22, and speech The database 23 is basically the same as in the first embodiment.

  In the present embodiment, the voice analysis function unit 13 determines whether identification information such as the telephone number of the other party to be called is registered as a voice synthesis target number in the telephone number book 21. The voice analysis function unit 13 also analyzes a voice signal based on the voice input to the voice input unit 17. That is, the voice analysis function unit 13 analyzes the spectrum of at least one voice signal of transmission or reception, and determines whether at least one voice of transmission or reception is a voice indicating a specific emotion such as anger. . Here, the spectrum of both the audio signal received from the receiving unit 12 and the audio signal based on the audio input to the audio input unit 17 is analyzed, and at least one of the analyzed audio signals is angry or the like. It is determined whether the audio signal indicates a specific emotion. Thereafter, the voice analysis function unit 13 sends a voice signal to the conversion function unit 14. At this time, if at least one of the voices of the transmission or reception is a voice indicating a specific emotion such as anger, the voice analysis function unit 13 indicates that the voice indicates a specific emotion or the original voice. The conversion function unit 14 is notified of an instruction for filtering. Note that the voice analysis function unit 13 unconditionally sends a voice signal to the conversion function unit 14 when it is not determined whether at least one of the voices of the transmission or reception is a voice indicating a specific emotion such as anger.

  The conversion function unit 14 refers to the keyword database 22 and outputs keyword data indicating a specific keyword according to the voice signal analyzed by the voice analysis function unit 13. Here, when the keyword included in the voice signal received from the voice input unit 17 is registered in the keyword database 22 as the NG word, the conversion function unit 14 sends a predetermined NG word to the voice output unit 16. Or a notification that it is an NG word. For example, when the keyword “XXX” included in the voice signal input by the user is registered as an NG word in the keyword database 22, the conversion function unit 14 receives the user via the voice output unit 16. Is notified that “XX is an NG word”. Note that the conversion function unit 14 may convert the voice of the NG word portion into silence or beep sound when the keyword included in the voice signal is registered in the keyword database 22 as an NG word. Moreover, the conversion function part 14 will perform the process (filtering) which outputs the audio | voice which filtered the original audio | voice if at least one audio | voice of transmission or reception is a voice which shows specific emotions, such as anger.

  The voice synthesis function unit 15 refers to the voice database 23 and synthesizes a predetermined voice according to the received voice signal. In the portable terminal of the present invention, the speech analysis function unit 13 and the conversion function unit 14 are arranged in the previous stage of the speech synthesis function unit 15.

  The telephone number book 21 stores identification information such as the telephone number of the other party who makes the call. Here, the telephone number book 21 stores identification information such as the telephone number of the other party who is the target of speech synthesis among the other parties who make a call. Note that the telephone number is merely an example, and in practice, it may be any identification information that can identify the other party to call. Moreover, the telephone number book 21 may be provided separately from the normal telephone number book which the portable terminal itself has.

  With reference to FIG. 5, the operation of the portable terminal in the present embodiment will be described.

(1) Step S301
The voice input unit 17 generates a voice signal in response to voice input when calling a predetermined partner. Here, the voice input unit 17 generates a voice signal in response to voice input by a user or an application, and sends the voice signal to the voice analysis function unit 13. At this time, the voice analysis function unit 13 receives the voice signal and the telephone number of the other party to call. For example, the voice analysis function unit 13 may receive a voice signal from the voice input unit 17 after receiving a telephone number input by the user.

(2) Step S302
The voice analysis function unit 13 determines whether the other party's telephone number to be called is registered in the telephone number book 21 as a voice synthesis target number. Note that the telephone number is merely an example, and in practice, it may be any identification information that can identify the other party to call.

(3) Step S303
The voice analysis function unit 13 directly sends a voice signal to the transmission unit 18 when the telephone number of the other party to be called is not a number registered as a voice synthesis target number in the telephone number book 21. At this time, the voice analysis function unit 13 may notify the conversion function unit 14 not to operate, and may send a voice signal to the transmission unit 18 via the conversion function unit 14. The transmission unit 18 modulates the received audio signal to convert it into a high frequency signal, and transmits the high frequency signal to the other party who makes a call via the antenna unit 11.

(4) Step S304
The voice analysis function unit 13 recognizes that the voice synthesis is ON when the telephone number of the other party to be called is a number registered in the telephone number book 21 as a voice synthesis target number, and operates the conversion function unit 14. For example, when the speech analysis function unit 13 recognizes that speech synthesis is ON, the speech analysis function unit 13 activates the conversion function unit 14 in the OFF state. Alternatively, the notification from the voice analysis function unit 13 to the conversion function unit 14 is changed from the prohibited state to the permitted state. That is, when the voice analysis function unit 13 recognizes that the voice synthesis is ON, the voice analysis function unit 13 can provide a voice signal to the conversion function unit 14 during a call with the other party.

(5) Step S305
The antenna unit 11 receives a high-frequency signal from the other party when the other party answers the call.

(6) Step S306
The receiving unit 12 demodulates the received high-frequency signal, converts it to a baseband signal, and sends it to the voice analysis function unit 13. At this time, the receiving unit 12 sends to the voice analysis function unit 13 an information signal indicating the telephone number of the other party who made the call together with the baseband signal. Here, the baseband signal is an audio signal. The baseband signal may include digital data indicating the telephone number of the other party who made the call.

(7) Step S307
The voice analysis function unit 13 analyzes the spectrum of at least one voice signal for transmission or reception, and determines whether at least one voice for transmission or reception is a voice indicating a specific emotion such as anger. That is, the voice analysis function unit 13 includes at least one of the voice signal received from the receiving unit 12 (voice signal from the other party) and the voice signal received from the voice input unit 16 (voice signal from the user side). It is determined whether the audio signal is an audio signal indicating a specific emotion such as anger. Thereafter, the voice analysis function unit 13 sends a voice signal to the conversion function unit 14. At this time, if at least one of the voices of the transmission or reception is a voice indicating a specific emotion such as anger, the voice analysis function unit 13 indicates that the voice indicates a specific emotion or the original voice. The conversion function unit 14 is notified of an instruction for filtering. If the voice analysis function unit 13 does not determine whether the voice indicates a specific emotion such as anger, the voice analysis function unit 13 sends a voice signal to the conversion function unit 14 unconditionally.

(8) Step S308
The conversion function unit 14 performs processing (filtering) to output a sound obtained by filtering the original voice if at least one of the voices of transmission or reception is a voice indicating a specific emotion such as anger. Here, the conversion function unit 14 sends the audio signal after filtering the original audio to the transmission unit 18. The transmission unit 18 outputs a sound obtained by filtering the original sound. At this time, the conversion function unit 14 sends a voice signal and a notification (filtering request) to filter the original voice to the voice synthesis function unit 15, and the voice synthesis function unit 15 filters the original voice. Alternatively, the voice synthesis function unit 15 may send the voice signal after filtering the original voice to the transmission unit 18.

(9) Step S309
If the voice of at least one of the transmission and reception is not a voice indicating a specific emotion such as anger, the conversion function unit 14 refers to the keyword database 22 and converts the voice signal analyzed by the voice analysis function unit 13 into It is determined whether or not keyword data indicating a specific keyword is included. At this time, if the voice signal analyzed by the voice analysis function unit 13 does not include keyword data indicating a specific keyword, the conversion function unit 14 sends the voice signal to the voice synthesis function unit 15.

(10) Step S310
When the speech signal analyzed by the speech analysis function unit 13 includes keyword data indicating a specific keyword, the conversion function unit 14 stops or prohibits speech synthesis for the speech synthesis function unit 15; A notification to output the original voice to the transmission unit 18 is sent. At this time, the voice synthesizing function unit 15 converts the voice of the part corresponding to the specific keyword in the voice signal into silence or beep and sends it to the transmission part 18, and sends the other part to the transmission part 18 with the original voice. Send to. The transmission unit 18 modulates the received audio signal to convert it into a high frequency signal, and transmits the high frequency signal to the other party who makes a call via the antenna unit 11.

(11) Step S311
When the voice signal analyzed by the voice analysis function unit 13 includes keyword data indicating a specific keyword, the conversion function unit 14 outputs the specific keyword to the voice output unit 16 based on the keyword data. To do. The voice output unit 16 outputs a specific keyword. For example, the conversion function unit 14 notifies the user via the voice output unit 16 that the specific keyword is an NG word based on the keyword data. At this time, the conversion function unit 14 may convert the sound of the NG word portion into silence or beep sound. Note that the conversion function unit 14 may not output the specific keyword to the voice output unit 16 when not notifying the user that the specific keyword is an NG word.

(12) Step S312
The speech synthesis function unit 15 refers to the speech database 23 and synthesizes speech similar to a specific person according to the received speech signal. Here, the speech synthesis function unit 15 synthesizes speech similar to a specific person with respect to the entire speech based on the received speech signal.

(13) Step S313
The voice synthesis function unit 15 sends the voice signal that has been voice synthesized to the transmission unit 18. The transmission unit 18 modulates the received audio signal to convert it into a high frequency signal, and transmits the high frequency signal to the other party who makes a call via the antenna unit 11.

(14) Step S314
The voice analysis function unit 13 continuously analyzes the emotion of at least one of the voices of the transmission or reception until the transmission of the high-frequency signal is completed, and the voice of at least one of the transmissions or receptions is specified as anger When the result of the voice indicating emotion is obtained, the output of the current synthesized sound is stopped and the process is switched to the process of outputting the voice obtained by filtering the original voice. The voice analysis function unit 13 ends the series of processes when the call is finished.

  In the mobile terminal according to the present embodiment, the voice can be decorated (decorated) using the voice color and dialogue as “material” like the emoticons and pictograms in the decoration mail (registered trademark).

<Fourth embodiment>
The fourth embodiment of the present invention will be described below.
In the third embodiment, when the speech signal analyzed by the speech analysis function unit 13 includes keyword data indicating a specific keyword, the conversion function unit 14 stops or prohibits speech synthesis, and NG In this embodiment, the speech synthesis is performed when the speech signal analyzed by the speech analysis function unit 13 includes keyword data indicating a specific keyword.

  The configuration of the mobile terminal in the present embodiment is basically the same as that in the third embodiment. That is, the configuration of the mobile terminal in the present embodiment is as shown in FIG.

  With reference to FIG. 6, the operation of the mobile terminal in the present embodiment will be described.

(1) Step S401
The voice input unit 17 generates a voice signal in response to voice input when calling a predetermined partner. Here, the voice input unit 17 generates a voice signal in response to voice input by a user or an application, and sends the voice signal to the voice analysis function unit 13. At this time, the voice analysis function unit 13 receives the voice signal and the telephone number of the other party (calling party) to call. For example, the voice analysis function unit 13 may receive a voice signal from the voice input unit 17 after receiving a telephone number input by the user.

(2) Step S402
The voice analysis function unit 13 determines whether the other party's telephone number to be called is registered in the telephone number book 21 as a voice synthesis target number. Note that the telephone number is merely an example, and in practice, it may be any identification information that can identify the other party to call.

(3) Step S403
The voice analysis function unit 13 sends a voice signal directly to the transmission unit 18 when the telephone number of the other party to be called is not a number registered as a voice synthesis target number in the telephone number book 21. At this time, the voice analysis function unit 13 may notify the conversion function unit 14 not to operate, and then may send a voice signal to the transmission unit 18 via the conversion function unit 14. The transmission unit 18 modulates the received audio signal to convert it into a high frequency signal, and transmits the high frequency signal to the other party who makes a call via the antenna unit 11.

(4) Step S404
The voice analysis function unit 13 recognizes that the voice synthesis is ON when the telephone number of the other party to be called is a number registered in the telephone number book 21 as a voice synthesis target number, and operates the conversion function unit 14. For example, when the speech analysis function unit 13 recognizes that speech synthesis is ON, the speech analysis function unit 13 activates the conversion function unit 14 in the OFF state. Alternatively, the notification from the voice analysis function unit 13 to the conversion function unit 14 is changed from the prohibited state to the permitted state. That is, when the voice analysis function unit 13 recognizes that the voice synthesis is ON, the voice analysis function unit 13 can provide a voice signal to the conversion function unit 14 during a call with the other party.

(5) Step S405
The antenna unit 11 receives a high-frequency signal from the other party when the other party answers the call.

(6) Step S406
The receiving unit 12 demodulates the received high-frequency signal, converts it to a baseband signal, and sends it to the voice analysis function unit 13. At this time, the receiving unit 12 sends to the voice analysis function unit 13 an information signal indicating the telephone number of the other party who made the call together with the baseband signal. Here, the baseband signal is an audio signal. The baseband signal may include digital data indicating the telephone number of the other party who made the call.

(7) Step S407
The voice analysis function unit 13 analyzes the spectrum of at least one voice signal for transmission or reception, and determines whether at least one voice for transmission or reception is a voice indicating a specific emotion such as anger. That is, the voice analysis function unit 13 includes at least one of the voice signal received from the receiving unit 12 (voice signal from the other party) and the voice signal received from the voice input unit 16 (voice signal from the user side). It is determined whether the audio signal is an audio signal indicating a specific emotion such as anger. Thereafter, the voice analysis function unit 13 sends a voice signal to the conversion function unit 14. At this time, if at least one of the voices of the transmission or reception is a voice indicating a specific emotion such as anger, the voice analysis function unit 13 indicates that the voice indicates a specific emotion or the original voice. The conversion function unit 14 is notified of an instruction for filtering. If the voice analysis function unit 13 does not determine whether the voice indicates a specific emotion such as anger, the voice analysis function unit 13 sends a voice signal to the conversion function unit 14 unconditionally.

(8) Step S408
The conversion function unit 14 performs processing (filtering) to output a sound obtained by filtering the original voice if at least one of the voices of transmission or reception is a voice indicating a specific emotion such as anger. Here, the conversion function unit 14 sends the audio signal after filtering the original audio to the transmission unit 18. The transmission unit 18 outputs a sound obtained by filtering the original sound. At this time, the conversion function unit 14 sends a voice signal and a notification (filtering request) to filter the original voice to the voice synthesis function unit 15, and the voice synthesis function unit 15 filters the original voice. Alternatively, the voice synthesis function unit 15 may send the voice signal after filtering the original voice to the transmission unit 18.

(9) Step S409
If the voice of at least one of the transmission and reception is not a voice indicating a specific emotion such as anger, the conversion function unit 14 refers to the keyword database 22 and converts the voice signal analyzed by the voice analysis function unit 13 into It is determined whether or not keyword data indicating a specific keyword is included. At this time, if the speech signal analyzed by the speech analysis function unit 13 includes keyword data indicating a specific keyword, the conversion function unit 14 outputs the speech signal to the speech synthesis function unit 15. Note that the conversion function unit 14 may output only a portion corresponding to a specific keyword in the speech signal to the speech synthesis function unit 15 and output the other portion to the transmission unit 18. Further, the conversion function unit 14 may output the keyword data to the speech synthesis function unit 15.

(10) Step S410
If the speech signal analyzed by the speech analysis function unit 13 does not include keyword data indicating a specific keyword, the conversion function unit 14 stops or prohibits speech synthesis for the speech synthesis function unit 15; A notification to output the original voice to the transmission unit 18 is sent. The transmission unit 18 outputs the original sound based on the sound signal.

(11) Step S411
When the voice signal analyzed by the voice analysis function unit 13 includes keyword data indicating a specific keyword, the conversion function unit 14 outputs the specific keyword to the voice output unit 16 based on the keyword data. To do. At this time, the conversion function unit 14 may output the synthesized sound corresponding to the specific keyword to the voice output unit 16 via the voice synthesis function unit 15. The audio output unit 16 notifies the user of a specific keyword. That is, the conversion function unit 14 notifies the user via the voice output unit 16 that voice synthesis is performed for a specific keyword based on the keyword data. Note that the conversion function unit 14 may not output the specific keyword to the voice output unit 16 when not notifying the user that speech synthesis is performed on the specific keyword.

(12) Step S412
The speech synthesis function unit 15 refers to the speech database 23 and synthesizes speech similar to a specific person according to the received speech signal. Here, the speech synthesis function unit 15 synthesizes speech similar to a specific person with respect to the entire speech based on the received speech signal. The voice synthesis function unit 15 receives the keyword data from the conversion function unit 14, and based on the keyword data, only the voice of the specific keyword included in the voice based on the received voice signal is used. You may make it perform a synthesis | combination. For example, if the keyword data indicates a prominent utterance of a specific person, the speech synthesis function unit 15, if the speech based on the received audio signal includes the same content as the prominent utterance, Only the part is synthesized with sound similar to a specific person.

(13) Step S413
The voice synthesis function unit 15 sends the voice signal that has been voice synthesized to the transmission unit 18. The transmission unit 18 modulates the received audio signal to convert it into a high frequency signal, and transmits the high frequency signal to the other party who makes a call via the antenna unit 11.

(14) Step S414
The voice analysis function unit 13 continuously analyzes the emotion of at least one of the voices of the transmission or reception until the transmission of the high-frequency signal is completed, and the voice of at least one of the transmissions or receptions is a specific signal such as anger. When the result of the voice indicating emotion is obtained, the output of the current synthesized sound is stopped and the process is switched to the process of outputting the voice obtained by filtering the original voice. The voice analysis function unit 13 ends the series of processes when the call is finished.

  It should be noted that the embodiments of the present invention can be implemented in combination.

  As described above, the mobile terminal of the present invention has a voice synthesis function, a voice synthesis switching function based on a voice of a specific keyword or a specific emotion, a filtering function to raw voice, and an automatic registration of a specific keyword. Has function.

  In the portable terminal of the present invention, the received sound can be heard with a synthesized sound imitating the voice of a specific person.

  In the portable terminal of the present invention, the voice synthesizer switching partner can be selected by registering the partner previously registered in the telephone number book 21, and voice synthesis can be turned on and off by pressing a switch during a call. .

  Further, in the mobile terminal of the present invention, when the voice of a specific keyword registered in the keyword database 22 is recognized, the voice synthesis can be stopped and the voice as the received voice can be outputted.

  In the portable terminal of the present invention, when a keyword is registered as an NG word, the NG word can be output to the other party.

Further, in the mobile terminal of the present invention, when the emotion of the received voice is analyzed and a result indicating that the voice indicates a specific emotion such as anger is obtained, the synthesized sound imitating the voice of the specific person is stopped. It is possible to perform processing to output a sound obtained by filtering the original sound.

  Further, in the portable terminal of the present invention, when a receiving operator presses a button, a voice before the predetermined time is analyzed and a specific keyword can be automatically registered in the keyword database 22.

  If this mobile terminal having the above functions is used, the demand of voice users whose profit ratio is decreasing can be stimulated, and the sales share of the mobile terminal can be increased.

  The present invention is considered to be used in mobile phone development and design companies and their departments.

  As mentioned above, although embodiment of this invention was explained in full detail, actually, it is not restricted to said embodiment, Even if there is a change of the range which does not deviate from the summary of this invention, it is included in this invention.

DESCRIPTION OF SYMBOLS 11 ... Antenna part 12 ... Reception part 13 ... Speech analysis function part 14 ... Conversion function part 15 ... Speech synthesis function part 16 ... Voice output part 17 ... Voice input part 18 ... Transmission part 21 ... Telephone number book 22 ... Keyword database 23 ... Voice database

Claims (15)

It is determined whether the identification information of the other party of voice communication is registered as a voice synthesis target, and when the identification information is registered as a voice synthesis target, the spectrum of the voice signal related to the voice communication is analyzed and based on the voice signal A voice analysis means for determining whether the voice corresponds to a voice pattern indicating a specific emotion;
When the voice is a voice corresponding to the voice pattern, a filtering process is performed to filter the voice, and the filtered voice is output. When the voice is not a voice corresponding to the voice pattern, the voice Conversion means for determining whether a keyword included in the signal corresponds to an NG word, and notifying that the keyword is an NG word to a source of the audio signal when the keyword corresponds to an NG word;
A mobile terminal comprising speech synthesis means for synthesizing predetermined speech with speech based on the speech signal and outputting synthesized speech. The mobile terminal according to claim 1,
The conversion means uses, as an NG word, a specific keyword included in an audio signal transmitted between the predetermined operation and a predetermined time before the predetermined time according to a predetermined operation of the user during the voice communication. A portable terminal that registers in a keyword database and refers to the keyword database when determining whether a keyword included in the audio signal corresponds to an NG word. The mobile terminal according to claim 1 or 2,
The voice analysis unit analyzes a spectrum of a voice signal on both a transmission side and a reception side in the voice communication, and a voice based on at least one voice signal of the transmission side and the reception side indicates a specific emotion To determine whether
The converting means performs a filtering process for filtering the sound indicating the specific emotion when the sound based on at least one sound signal of the transmitting side and the receiving side is a sound corresponding to the sound pattern. Do mobile device. The mobile terminal according to any one of claims 1 to 3,
The said conversion means judges whether the keyword contained in the said audio | voice signal corresponds to a specific keyword, and when the said keyword corresponds to a specific keyword, the said audio | voice signal is sent to the said voice synthesizing means. The mobile terminal according to any one of claims 1 to 4,
The converting means determines whether a keyword included in the audio signal corresponds to a specific keyword, and if the keyword corresponds to a specific keyword, the audio signal at a location corresponding to the specific keyword is selected from the audio signals. , Sent to the speech synthesis means,
The portable terminal that synthesizes a predetermined voice with respect to a voice signal corresponding to a specific keyword in the voice signal and outputs a synthesized voice. Determine whether the identification information of the voice communication partner is registered as the target for speech synthesis,
When the identification information is registered as a voice synthesis target, analyze a spectrum of a voice signal related to the voice communication, determine whether the voice based on the voice signal is a voice indicating a specific emotion,
If the voice is a voice corresponding to the voice pattern, perform a filtering process to filter the voice, and output the filtered voice,
If the voice is not a voice corresponding to the voice pattern, it is determined whether a keyword included in the voice signal corresponds to an NG word. If the keyword corresponds to an NG word, the voice signal source is Notify that the keyword is an NG word,
A speech synthesis method for synthesizing predetermined speech with speech based on the speech signal and outputting synthesized speech. The speech synthesis method according to claim 6,
During the voice communication, a specific keyword included in a voice signal transmitted between the predetermined operation and a predetermined time before is registered as an NG word in the keyword database according to a predetermined operation of the user. ,
A speech synthesis method for referring to the keyword database when determining whether a keyword included in the speech signal corresponds to an NG word. The speech synthesis method according to claim 6 or 7,
The voice analysis unit analyzes a spectrum of a voice signal on both a transmission side and a reception side in the voice communication, and a voice based on at least one voice signal of the transmission side and the reception side indicates a specific emotion To determine whether
A speech synthesizing method that performs a filtering process for filtering the speech indicating the specific emotion when speech based on at least one speech signal of the transmitting side and the receiving side is speech that corresponds to the speech pattern. The speech synthesis method according to any one of claims 6 to 8,
Determining whether a keyword included in the audio signal corresponds to a specific keyword;
A speech synthesis method for synthesizing predetermined speech with respect to the speech signal and outputting a synthesized speech when the keyword corresponds to a specific keyword. The speech synthesis method according to any one of claims 6 to 9,
Determining whether a keyword included in the audio signal corresponds to a specific keyword;
When the keyword corresponds to a specific keyword, a voice synthesis method for synthesizing a predetermined voice with respect to a voice signal at a location corresponding to the specific keyword in the voice signal and outputting a synthesized voice. Determining whether the identification information of the voice communication partner is registered as a speech synthesis target;
When the identification information is registered as a voice synthesis target, the spectrum of the voice signal related to the voice communication is analyzed to determine whether the voice based on the voice signal is a voice corresponding to a voice pattern indicating a specific emotion. Steps,
If the voice is a voice corresponding to the voice pattern, performing a filtering process to filter the voice, and outputting the filtered voice;
If the voice is not a voice corresponding to the voice pattern, it is determined whether a keyword included in the voice signal corresponds to an NG word. If the keyword corresponds to an NG word, the voice signal source is Notifying that the keyword is an NG word;
A speech synthesis program for causing a computer to execute a step of synthesizing predetermined speech with speech based on the speech signal and outputting the synthesized speech. The speech synthesis program according to claim 11,
During the voice communication, a specific keyword included in a voice signal transmitted between the predetermined operation and a predetermined time before is registered in the keyword database as an NG word according to a predetermined operation of the user. Steps,
A speech synthesis program for causing a computer to further execute a step of referring to the keyword database when determining whether or not a keyword included in the speech signal corresponds to an NG word. The speech synthesis program according to claim 11 or 12,
The voice analysis unit analyzes a spectrum of a voice signal on both a transmission side and a reception side in the voice communication, and a voice based on at least one voice signal of the transmission side and the reception side indicates a specific emotion Determining whether the sound corresponds to the pattern;
A step of performing a filtering process for filtering the voice indicating the specific emotion when the voice based on at least one voice signal of the transmitting side and the receiving side is a voice corresponding to the voice pattern; A speech synthesis program to be executed by a computer. A speech synthesis program according to any one of claims 11 to 13,
Determining whether a keyword included in the audio signal corresponds to a specific keyword;
A speech synthesis program for causing a computer to further execute a step of synthesizing predetermined speech with respect to the speech signal and outputting a synthesized sound when the keyword corresponds to a specific keyword. A speech synthesis program according to any one of claims 11 to 14,
Determining whether a keyword included in the audio signal corresponds to a specific keyword;
When the keyword corresponds to a specific keyword, the computer further executes a step of synthesizing a predetermined voice with respect to a voice signal at a position corresponding to the specific keyword in the voice signal and outputting a synthesized voice. A program for speech synthesis.

Images