JP4957119B2 - Information processing device - Google Patents

Description

  The present invention relates to an information processing apparatus, and more particularly, to an information processing apparatus capable of making a videophone call.

  2. Description of the Related Art In recent years, videophone systems that exchange large volumes of image data and audio data between users via the Internet are known.

  For example, when the video phone system is used between the user A and the user B, the user A's computer A displays the image of the user B transmitted from the user B's computer B and outputs sound. Further, the computer B of the user B displays the image of the user A transmitted from the computer A of the user A and outputs a sound. Thereby, the communication by an image and an audio | voice can be aimed between the user A and the user B. FIG. This videophone system can be applied not only to one-to-one but also to one-to-one.

  In addition to the video phone system, a video conference system and the like are known as a method for communication using images and sounds.

  In a video conference system that performs one-to-multiple video and audio communication, in response to a command from the terminal, the video material stored in advance is read out and combined with the video from each terminal into a single video. A technology has been proposed that can be used to display and use the stored document video and past video in a desired format as well as the video from the video, or to accumulate and display the conference history in a desired format. (For example, refer to Patent Document 1).

On the other hand, in recent years, a technique for making a videophone call between mobile phones by wireless communication via a base station or the like has also been proposed for mobile phones. In particular, between mobile phones, a one-to-one videophone is currently in practical use.
JP 2001-313915 A

  However, when making a one-to-multiple videophone call on a mobile phone (that is, when making a videophone call between multiple points), the size of the display unit provided on the mobile phone is limited. If all the faces are displayed on the display unit, the display area allocated per person becomes small, and it is difficult to determine who the person is even if the face of the other party is displayed. there were.

  Such a problem cannot be solved even by the technique proposed in Patent Document 1.

  The present invention is made in view of such a situation, and when a plurality of users make a videophone call between multiple points, it is preferable to arrange a user image displayed on the display unit according to a call situation. It is an object of the present invention to provide an information processing apparatus that can be controlled automatically.

In order to solve the above-described problem, the information processing apparatus according to the present invention acquires an image signal and a sound signal from a plurality of information processing apparatuses, and performs speech recognition processing based on the acquired sound signal. The display means for displaying an image based on a plurality of image signals, and the number of times the name is called is analyzed based on the speech recognized by the voice recognition means, and the display means displays the result based on the analysis result. Analyzing means for calculating priority for image arrangement based on a plurality of image signals, and control for controlling arrangement of images based on the plurality of image signals displayed by the display means in accordance with the priority calculated by the analyzing means Means.

In the information processing apparatus of the present invention, image signals and audio signals are respectively acquired from the plurality of information processing apparatuses, and voice recognition processing is performed based on the acquired audio signals, and images based on the plurality of image signals are displayed. Based on the speech-recognized utterance, the number of times the name is called is analyzed, and based on the analysis result, the priority for the arrangement of the images based on the plurality of displayed image signals is calculated, and the calculated priority The arrangement of images based on a plurality of displayed image signals is controlled according to the degree.

  ADVANTAGE OF THE INVENTION According to this invention, when a some user makes a videophone between many points, arrangement | positioning of the user's image displayed on a display part according to a telephone call condition can be controlled suitably.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  FIG. 1 shows an internal configuration of a mobile phone 1 applicable as an information processing apparatus according to the present invention.

  As shown in FIG. 1, the mobile phone 1 has a power supply circuit unit 22, an operation input control unit 23, an image encoder 24, and a camera interface unit with respect to a main control unit 21 that comprehensively controls each unit of the mobile phone 1. 25, an LCD (Liquid Crystal Display) control unit 26, a demultiplexing unit 28, a modulation / demodulation circuit unit 29, an audio codec 30, a storage unit 37, and a music control unit 38 are connected to each other via a main bus 31, and an image encoder 24, an image decoder 27, a demultiplexing unit 28, a modulation / demodulation circuit unit 29, an audio codec 30, and a recording / reproducing unit 35 are connected to each other via a synchronization bus 32.

  When the call termination / power key is turned on by the user's operation, the power supply circuit unit 22 activates the mobile phone 1 by supplying power from the battery pack to each unit.

  The main control unit 21 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). The CPU is loaded into the RAM from a program stored in the ROM or the storage unit 37. In addition to executing various processes in accordance with various application programs, the mobile phone 1 is comprehensively controlled by generating various control signals and supplying them to the respective units. The RAM appropriately stores data necessary for the CPU to execute various processes.

  The main control unit 21 has a built-in timer that measures the current date and time.

  Here, various application programs executed by the CPU can be installed in the ROM or the storage unit 37 in advance. Various application programs executed by the CPU can be installed in the storage unit 37 by downloading to the mobile phone 1 by communication via a base station (not shown). Furthermore, various application programs executed by the CPU can be recorded in the memory card 36, read out by the recording / playback unit 35, and installed in the storage unit 37.

  Based on the control of the main control unit 21, the cellular phone 1 converts the voice signal collected by the microphone 15 in the voice call mode into a digital voice signal by the voice codec 30, compresses it, and spreads the spectrum by the modulation / demodulation circuit unit 29. Then, after the digital / analog conversion process and the frequency conversion process are performed by the transmission / reception circuit unit 33, the signal is transmitted via the antenna 34.

  Also, the cellular phone 1 amplifies the received signal received by the antenna 34 in the voice call mode, performs frequency conversion processing and analog-digital conversion processing, performs spectrum despreading processing by the modulation / demodulation circuit unit 29, and decompresses it by the voice codec 30. After the conversion to an analog audio signal, the converted analog audio signal is output via the speaker 16.

  When the mobile phone 1 does not transmit an image signal, the mobile phone 1 directly displays the image signal captured by the CCD camera 12 on the liquid crystal display 13 via the camera interface unit 35 and the LCD control unit 36.

  When transmitting an image signal in the data communication mode (or when making a videophone call), the mobile phone 1 supplies the image signal captured by the CCD camera 12 to the image encoder 24 via the camera interface unit 25.

  The image encoder 24 converts the image signal supplied from the CCD camera 12 into an encoded image signal by compressing and encoding the image signal using a predetermined encoding method such as MPEG (Moving Picture Experts Group) 4, for example. The encoded image signal is sent to the demultiplexing unit 28. At the same time, the cellular telephone device 1 sends out the sound collected by the microphone 15 during imaging by the CCD camera 12 as a digital audio signal via the audio codec 30.

  The demultiplexing unit 28 multiplexes the encoded image signal supplied from the image encoder 24 and the audio signal supplied from the audio codec 30 by a predetermined method, and the resulting multiplexed signal is converted into a spectrum by the modulation / demodulation circuit unit 29. The signal is subjected to spreading processing, subjected to digital / analog conversion processing and frequency conversion processing by the transmission / reception circuit unit 33, and then transmitted through the antenna 34.

  Further, when receiving data of a moving image file in the data communication mode (or when making a videophone call), the mobile phone 2 modulates a demodulation signal received from a base station (not shown) via the antenna 34. The unit 29 performs spectrum despreading processing, and sends the resulting multiplexed signal to the demultiplexing unit 28.

  The demultiplexing unit 28 divides the multiplexed signal into an encoded image signal and an audio signal, supplies the encoded image signal to the image decoder 27 via the synchronization bus 32, and supplies the audio signal to the audio codec 30. Supply. The image decoder 27 generates a reproduction moving image signal by decoding the encoded image signal by a decoding method corresponding to a predetermined encoding method such as MPEG4, and sends the generated reproduction moving image signal to the LCD control unit 36. To the liquid crystal display 13. Thereby, for example, moving image data included in the moving image file is displayed.

  At the same time, the audio codec 30 converts the audio signal into an analog audio signal, and then supplies the analog audio signal to the speaker 16, thereby reproducing, for example, the audio signal included in the moving image file.

  The storage unit 37 includes, for example, a flash memory element that is an electrically rewritable and erasable nonvolatile memory, and stores various application programs executed by the CPU of the main control unit 21 and various data groups. ing. In addition, the storage unit 37 stores e-mail received in response to a user operation, moving image data included in a moving image file linked to the received Web page, and the like as necessary.

  The music control unit 38 controls the execution of a reproduction operation and a pause operation of the audio data stored in the storage unit 37, a rewind function, a fast forward function, a volume down operation, a volume up operation, and the like.

  FIG. 2 shows a functional configuration that can be executed by the mobile phone 1 applicable to the information processing apparatus according to the present invention.

  The voice recognition function 41 is realized by, for example, the main control unit 21 in FIG. 1, and acquires a voice signal (digital signal) expanded by the voice codec 30 within a predetermined time (for example, 5 minutes). Then, the invalid sound and noise are removed from the obtained decompressed voice signal, and voice recognition processing is executed based on the voice signal after the invalid sound and noise are removed. In other words, the voice recognition function 41 extracts a feature amount from the voice signal from which invalid sounds and noises have been removed, and a predetermined word string is uttered by a participant of the videophone based on the extracted feature amount (voice). ), And utterance data, which is data relating to the utterance (voice) of the participant of the selected videophone, is sequentially supplied to the analysis function 42.

  The analysis function 42 is realized by, for example, the main control unit 21 of FIG. 1, and sequentially acquires the speech data of the videophone participant supplied from the voice recognition function 41, and the acquired speech data of the videophone participant is acquired. Based on the above, a predetermined analysis (analysis of the number of utterances of a videophone participant or the number of utterances of a keyword) is performed. Based on the analysis result, the analysis function 42 updates the utterance history database 43 in which the participant of the videophone and the utterance count of the participant are registered in association with each other at a predetermined time. At the same time, referring to the updated message history database 43, the priority regarding the arrangement of the image of the participant of the videophone displayed on the liquid crystal display 13 according to the current call status is calculated, and the calculated priority Priority data that is data relating to the image is supplied to the image arrangement control function 44. Note that the speech history database 43 is realized by, for example, the storage unit 37 of FIG.

  The image arrangement control function 44 is realized by, for example, the main control unit 21 in FIG. 1 and the like, acquires the priority data supplied from the analysis function 42, and performs a liquid crystal display when performing a videophone call based on the acquired priority data. An image arrangement control signal for controlling the arrangement of the images of the videophone participants displayed on the display 13 is generated, and the generated image arrangement control signal is supplied to the LCD control unit 26.

  Next, the flowchart of FIG. 3 shows image arrangement control processing in the mobile phone 1 of FIG. Note that this image arrangement control processing is performed simultaneously when a plurality of users (for example, four users including Mr. A, Mr. B, Mr. C, and Mr. D) start a videophone (or a video conference). And start.

  In step S1, the voice recognition function 41 sequentially acquires voice signals (digital signals) expanded by the voice codec 30 within a predetermined time (for example, 5 minutes) set in advance. For example, when making a videophone call between four users including Mr. A, Mr. B, Mr. C, and Mr. D, a plurality of mobile phones 1 (in addition to the mobile phones 1 of other users) In the audio signal and the image signal acquired from the telephone 1 (including the telephone 1), at least control information (for example, the telephone number of the mobile telephone 1) indicating which mobile telephone 1 is the audio signal or the image signal is included. Based on this control information, it is possible to determine from which mobile phone 1 performing a videophone call an audio signal or an image signal.

  In step S2, the speech recognition function 41 removes invalid sounds and noises from the acquired decompressed speech signals, and executes speech recognition processing based on the speech signals after the invalid sounds and noises are removed. To do. In other words, the voice recognition function 41 extracts a feature amount from the voice signal from which invalid sounds and noises are removed, and a predetermined word string is extracted from the extracted feature amount as a videophone participant (Mr. A, The voice (voice) of any of Mr. B, Mr. C, and Mr. D) is selected.

  For example, when Mr. B says to Mr. A, “It ’s XX, Mr. A”, the voice recognition process is executed, so that one of the four participants in the videophone call says “XX. “Mr. A” is selected.

  The speech recognition function 41 sequentially supplies speech data, which is data relating to speech (speech) of the selected videophone participant, to the analysis function 42. In this message data, for example, the data related to “XX, Mr. A” selected as the message of one of the four videophone participants, and the voice signal from which mobile phone 1 are used. Control information (for example, a telephone number of the mobile phone 1) is included.

  In step S3, the analysis function 42 sequentially acquires the utterance data of the videophone participant supplied from the voice recognition function 41, and performs a predetermined analysis (TVV) based on the acquired utterance data of the videophone participant. Analysis of the number of utterances of telephone participants and the number of utterances of keywords).

  Specifically, first, the analysis function 42 identifies the participant of the videophone based on the acquired speech data of the participant of the videophone. That is, for example, as shown in FIG. 4, when Mr. B says to Mr. A, “You are XX, Mr. A,” then Mr. A says to Mr. B, “Yes, yes.” When (response) is made, it is possible to specify that the participant of the videophone who made the speech (response) is “Mr. A”. By the same processing, Mr. B, Mr. C, and Mr. D can be specified.

  FIG. 4 shows the correspondence between the telephone number of the mobile phone 1 owned by the user participating in the videophone and the participant name.

  In the first column to the second column of the table in FIG. 4, “phone number” and “participant name” are described in order from the left, and each participant (user) participating in the videophone call is described. ) And the participant name corresponding to the telephone number of the mobile phone 1.

  In the first row of the table of FIG. 4, the “phone number” is “090-2345-xxx”, and the phone number of the mobile phone 1 owned by the user participating in the videophone is “090-”. 2345-xxxx ”. The “participant name” is “A”, which indicates that the participant name corresponding to the telephone number (“090-2345-xxx”) of the mobile phone 1 is “A”.

  In the second row of the table of FIG. 4, the “phone number” is “090-7523-xxx”, and the phone number of the mobile phone 1 owned by the user participating in the videophone is “090- 7523-xxx ”. “Participant name” is “B”, which indicates that the participant name corresponding to the telephone number (“090-7523-xxx”) of the mobile phone 1 is “B”.

  Note that the same applies to the third to fourth rows of the table of FIG.

  Next, the analysis function 42 selects the current talk among the participants of the videophone based on the control information (for example, the telephone number of the mobile phone 1) included in the acquired speech data of the participant of the videophone. Identify the person. For example, when the current speaker is Mr. A (the user who owns the mobile phone 1 whose telephone number is “090-2345-xxx”) among the participants of the videophone, the remarks of the participant of the videophone Based on the control information included in the data (the telephone number of the mobile phone 1 of “090-2345-xxx”), the current speaker is identified as Mr. A.

  FIG. 5 shows the correspondence between the telephone number of the mobile phone 1 owned by the user participating in the videophone, the name of the participant, and the speaker who is speaking. The “phone numbers” and “participant names” in the first and second columns of the table of FIG. 5 are the “telephone numbers” and “ This is the same as “Participant Name”, and the description thereof will be omitted because it will be repeated.

  In the third column of the table of FIG. 5, “speaking” is described, indicating whether or not the speaker is currently speaking.

  In the case of the first row of the table of FIG. 5, “in speech” is “◯”, indicating that the user with the participant name “A” is the speaker who is currently speaking.

  In the case of the second row of the table of FIG. 5, “speaking” is “−”, indicating that the user with the participant name “B” is not the speaker currently speaking.

  Note that the same applies to the third to fourth rows of the table of FIG.

  Of course, if there are multiple (for example, two) current speakers among the participants of the videophone, the plurality of participants are currently selected based on the control information included in the speech data of the participants of the videophone. Identified as a speaker.

  Further, the analysis function 42 is based on the acquired utterance data of the participants of the videophone, and the number of utterances of the four participants A to D, the number of utterances of the keywords within a predetermined time set in advance, Analyze the number of times the name is called and the number of times the answer (including the answer) is made. As a result, even if it is not a speaker, for example, if the number of utterances, the number of utterances of a keyword, and the number of times a name is called are large, it can be recognized as a central person of conversation (or a person close to the central person of conversation) In addition, if the number of replies is large, it can be recognized that the player is a partner in the conversation.

  The keyword may be a word that is repeatedly used in the content of a videophone conversation, or may be set in advance according to the user's preference.

  FIG. 6 shows the telephone number of the mobile phone 1 owned by the user participating in the videophone, the name of the participant, the speaker who is speaking, the number of utterances, the number of utterances of the keyword, the number of times the name is called, and the reply It shows the correspondence of the number of times. Note that “phone numbers”, “participant names”, and “speaking” in the first to third columns of the table of FIG. 6 are the first to third columns of the table of FIG. This is the same as “telephone number”, “participant name”, and “speaking”, and a description thereof will be omitted.

  In the fourth column to the eighth column of the table of FIG. 6, “the number of utterances”, “the number of utterances of the keyword”, “the number of times the name is called”, and “the number of replies” are described in order from the left. The number of times a videophone participant speaks during a conversation, the number of times a keyword related to a certain theme when making a videophone call, the number of times a name is called by another participant, and other participation The number of times the person has been answered.

  In the case of the first row in the table of FIG. 6, the “speech count” is “7”, and the videophone participant (participant A) speaks during the conversation is “7”. Yes. “Keyword utterance count” is “3”, which indicates that the number of utterances of a keyword related to a predetermined theme when making a videophone call is “3”. “The number of times the name is called” is “6”, which indicates that the number of times the name (named “Mr. A”) is called by another participant is “6”. “Number of replies” is “5”, indicating that the number of replies to other participants is “5”.

  In the case of the second row of the table of FIG. 6, the “number of utterances” is “1”, and the number of utterances during the conversation by the participant (participant B) of the videophone is “1”. Yes. “Keyword utterance count” is “1”, which indicates that the number of utterances of keywords related to a predetermined theme when making a videophone call is “1”. The “number of times the name is called” is “2”, indicating that the number of times the name (named “Mr. A”) is called by another participant is “2”. “Number of replies” is “2”, indicating that the number of replies to other participants is “2”.

  Note that the same applies to the third to fourth rows of the table of FIG.

  In step S4, the analysis function 42 updates the utterance history database 43 in which videophone participants and the number of utterances are registered in association with each other based on the analysis result at predetermined time intervals set in advance. To do.

  For example, when the utterance history database 43 is updated based on the analysis results as shown in the table of FIG. 6 when four people A to D make a videophone call, the utterance history database as shown in FIG. 43 is updated.

  For example, when a videophone call is started with four participants A to D, the image arrangement control process is repeated at a predetermined time set in advance, and the speech history database 43 is stored as shown in FIG. After the update, when a predetermined time set in advance elapses, the message history database 43 is updated as shown in FIG. 8, for example.

  In the case of the example in FIG. 8, the user with the participant name “D” is the speaker who is currently speaking, and the other “number of utterances”, “number of keyword utterances”, “number of times the name is called”, and “Number of replies” has been updated.

  In the embodiment of the present invention, a speech recognition process is performed based on a speech signal acquired within a predetermined time set in advance, and the speech (speech) that has been speech-recognized is collectively analyzed. On the basis of the result, the utterance history database 43 in which the participants of the videophone and the number of utterances are registered in association with each other is updated in batches at predetermined time intervals. However, the present invention is not limited to this, and it is also possible to sequentially perform speech recognition processing based on sequentially acquired speech signals, sequentially analyze speech-recognized speech (speech), and update the speech history database 43 sequentially.

  In step S5, the analysis function 42 refers to the updated message history database 43 and displays the image of the videophone participant (for example, A to D) displayed on the liquid crystal display 13 according to the current call status. The priority relating to the arrangement (that is, the degree of priority on the display screen on the liquid crystal display 13 because the frequency and importance of the conversation are high in the videophone with four participants A to D) is calculated.

  Specifically, in the case of the example in FIG. 7, since the participant A is a speaker who is currently speaking, for example, among the four participants A to D, the highest priority is calculated for the participant A The priority is calculated in the order of the remaining participants C, D, and B (participant B is calculated with the lowest priority). In calculating the priority, the number of utterances, the number of replies, and the like may be simply added, or may be added after weighting for each number of times.

  The analysis function 42 supplies priority data, which is data relating to the calculated priority, to the image arrangement control function 44.

  In step S6, the image arrangement control function 44 acquires the priority data supplied from the analysis function 42, and the participant displayed on the liquid crystal display 13 when making a videophone call based on the acquired priority data. An image arrangement control signal for controlling the arrangement of the images (A to D in the example of FIG. 7) is generated, and the generated image arrangement control signal is supplied to the LCD control unit 26.

  For example, in the case of the example of FIG. 7, since the participant A is a speaker who is currently speaking, the highest priority is calculated for the participant A among the four participants A to D. For example, FIG. As shown, the participant A's image is displayed on the main X-1, while the other participants B to D participate in the sub-X-2 to 4 below the main X-1. An image arrangement control signal for controlling the arrangement of the person's image is generated.

  The LCD control unit 26 acquires a plurality of decoded image signals supplied from the image decoder 27, and acquires the plurality of decoded images obtained based on the image arrangement control signal supplied from the image arrangement control function 44. An image of a participant (for example, A to D) based on the signal is arranged at a desired position and displayed on the liquid crystal display 13.

  In step S7, the liquid crystal display 13 controls the images of the participants (for example, A to D) based on a plurality of decoded image signals as shown in FIG. Update and display every hour.

  Thereby, the user can easily determine the face of the user who is the center of conversation in the videophone (or the user who is speaking), and the user who is the center of conversation in the videophone (or It is possible to easily recognize who the user is speaking).

  In steps S6 and S7, for example, in the example of FIG. 7, the participant A is a speaker who is currently speaking, and the highest priority is calculated for the participant A, and then the participants C, D Since the priority is calculated in the order of B and B, for example, as shown in FIG. 10, the image of the participant A is displayed on the main X-1, and the image of the participant C is below the main X-1. Is displayed on the slightly larger sub X-2, the image of the participant D is displayed on the slightly larger sub X-3 below the main X-1, and the image of the participant B is displayed below the main X-1. An image arrangement control signal for controlling the arrangement of the images of the participants may be generated so as to be displayed in the slightly larger sub X-4.

  Further, for example, when ten people make a videophone call, when it is recognized that the participant A is called many times by other participants and the conversation is centered on the participant A, for example, FIG. Thus, the image of the participant A is displayed on the main X-4, and the images of the other high-priority participants (B to G) that are recognized as the conversation partner of the participant A are sub-X. Image arrangement control signals for controlling the arrangement of the images of the participants may be generated so as to be displayed on -1 to X-3 and X-5 to X-7.

  Thereafter, the process returns to step S1, and the processes after step S1 are repeated.

  In the embodiment of the present invention, voice recognition processing is performed based on voice signals acquired from a plurality of mobile phones 1, and predetermined analysis is performed based on utterance data which is data related to voice-recognized utterances. Based on the analysis result, the priority regarding the arrangement of the image of the participant of the videophone displayed on the liquid crystal display 13 is calculated, and the arrangement of the image of the participant displayed on the liquid crystal display 13 is calculated based on the calculated priority. Therefore, when a plurality of users make a videophone call between multiple points, the arrangement of the user images displayed on the display unit (liquid crystal display 13) is preferably controlled according to the call status. Can do. Thereby, even when the size of the display unit is limited as in the mobile phone 1, the user can easily see the face of the user (or the user who is speaking) who is the center of conversation in the videophone. It is possible to discriminate, and it is possible to easily recognize who is the user (or the user who is speaking) who is the center of conversation in the videophone. Therefore, the convenience in making a videophone call can be improved.

  In addition, “call situation” means various situations in videophone calls performed by a plurality of users, for example, who is the current speaker, how many times the speaker speaks, who is the central person in the conversation, The content of the conversation is defined as a situation regarding what kind of content it is.

  In addition, in the image arrangement control process described with reference to FIG. 3, the participation displayed on the liquid crystal display 13 at a predetermined time (for example, 5 minutes) according to the current call status. Although the arrangement of the person's image is controlled, the predetermined time for repeating the image arrangement control process may be changed according to the contents of the videophone call and the participants.

  The present invention can be applied to a PDA (Personal Digital Assistant), a personal computer, and other information processing apparatuses in addition to the mobile phone 1.

  The series of processes described in the embodiments of the present invention can be executed by software, but can also be executed by hardware.

  Furthermore, in the embodiment of the present invention, the steps of the flowchart show an example of processing performed in time series in the order described, but parallel or individual execution is not necessarily performed in time series. The processing to be performed is also included.

1 is a block diagram showing an internal configuration of a mobile phone applicable to an information processing apparatus according to the present invention. The block diagram which shows the functional structure which the mobile telephone applicable to the information processing apparatus which concerns on this invention can perform. 3 is a flowchart for explaining image arrangement control processing in the mobile phone of FIG. 2. The figure which shows the correspondence of the telephone number of the mobile telephone which the user who has participated in the videophone, and a participant name. The figure which shows the correspondence of the telephone number of the mobile telephone which the user who has participated in the videophone, a participant name, and the speaker who is speaking. Correspondence relationship between the phone number of the mobile phone owned by the user participating in the videophone, the name of the participant, the speaker who is speaking, the number of utterances, the number of utterances of the keyword, the number of times the name is called, and the number of replies FIG. The figure which shows the structural example of the speech log | history database of FIG. The figure which shows the other structural example of the speech log | history database of FIG. The figure which shows the example of arrangement | positioning of the image of the participant displayed on the liquid crystal display of FIG. The figure which shows the other example of arrangement | positioning of the image of the participant displayed on the liquid crystal display of FIG. The figure which shows the other example of arrangement | positioning of the image of the participant displayed on the liquid crystal display of FIG.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Mobile phone, 11 ... Operation key, 12 ... CCD camera, 13 ... Liquid crystal display, 14 ... Sub-display, 15 ... Microphone, 16 ... Speaker, 21 ... Main control part, 22 ... Power supply circuit, 23 ... Operation input control part , 24 ... Image encoder, 25 ... Camera I / F unit, 26 ... LCD control unit, 27 ... Image decoder, 28 ... Demultiplexing unit, 29 ... Modulation / demodulation circuit unit, 30 ... Audio codec, 31 ... Main bus, 32 ... Synchronization Bus 33, transmission / reception circuit unit 34 34 antenna 35 recording / reproduction unit 36 memory card 37 storage unit 38 music control unit 41 speech recognition function 42 analysis function 43 speech history database 44. Image layout control function.

Claims (4)

In an information processing apparatus that performs videophone calls between multiple points via wireless communication,
Voice recognition means for acquiring image signals and voice signals from the plurality of information processing apparatuses, and performing voice recognition processing based on the acquired voice signals;
Display means for displaying an image based on a plurality of the image signals;
Based on the speech voice-recognized by the voice recognition means, the number of times the name is called is analyzed, and based on the result of the analysis, the priority regarding the arrangement of the images based on the plurality of image signals displayed by the display means An analysis means for calculating
An information processing apparatus comprising: control means for controlling arrangement of images based on the plurality of image signals displayed by the display means according to the priority calculated by the analysis means. Wherein the by the analysis result analyzing means, say the number of times, claim, characterized in that contained speech number of keywords, at least one of the number of times of the return that is 1
The information processing apparatus described in 1.   2. The information processing according to claim 1, wherein the control unit performs control to enlarge and arrange an image based on the plurality of image signals displayed by the display unit as the priority is higher. apparatus.   The information processing apparatus according to claim 1, further comprising storage means for storing an analysis result by the analysis means.

Images