JP2010266880A - Mobile terminal device, information processing method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To automatically extract upsurge parts which are demanded by a viewer from sound signals and integrate them, or reproduce such the upsurge parts. <P>SOLUTION: In an information providing device 10, an importance determination section 11 investigates frequency strength distribution of the sound signals for each predetermined time section, when TV broadcasting is received, and determines, for example, a part where similarity is a threshold or more as an important part by matching the frequency strength distribution with the frequency strength distribution registered as an important pattern beforehand; an extracting section 12 extracts the video/sound of the part or before and after the part which is determined to be important in the importance determination section 11, and records the part in a recording section 13 separately from an original video/sound signal, by copying the part; an integrating section 14 for integrating the important part recorded in the recording section 13 time-sequentially or in an arbitrary order; and a transmission section 15 transmits the important part integrated by the integrating section 14 to the viewer, for example, the user of a mobile telephone or the like. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to an information processing apparatus and a portable terminal device that extract a rising part of an audio signal in television broadcasting or the like as an important part or reproduce the important part.

  In broadcasting using general public broadcasting, it is generally kept flowing as its information form, and the viewer selects and watches a desired program from these. However, the viewer usually has a particularly interesting part or an area of interest. For example, in a sports program, it is important to watch from the start of a certain competition until the final victory or defeat is decided, but the moment when the score is scored or the goal is scored is particularly interesting for the viewer. It's common to think that you just don't want to miss. For this reason, a broadcasting station often creates a digest video such as a special program or a summary edited by cutting out and editing only the part desired by the viewer, and broadcasting it as another program after the competition is over.

  Conventionally, such a digest video can be created by manually editing a video while watching a video, creating a digest video, or manually indexing the content and using the index. A common method is to search and create a digest video. However, in such a method, since it is necessary for a human to view the entire video, much time and labor are required.

  Furthermore, with the development of network technology in recent years, so-called broadband, such as ADSL and optical connection, has begun to spread, and not only watching broadcasts using television receivers but also watching so-called streaming programs via networks has increased. I came. However, even in such digest video streamed over the network, humans have traditionally created it manually, and many of the media for public broadcasting are simply converted for use via the network. Time and effort were needed.

  For this reason, the following Patent Document 1 automatically detects a rising part of an event such as a sport by combining the power level of the entire frequency band and the power level of a specific frequency component, A technique for providing an index has been proposed. In this technique, since the sound that the audience has excited is detected, it can be applied universally to many events, and it is possible to automatically detect important points in the progress of the event.

JP 2001-143451 A

  However, since the technique described in Patent Document 1 only adds an index to the swelled portion, when the video / audio signal with such an index is distributed to, for example, a user of the mobile terminal device, the user performs a digest. In order to view the video, it was necessary to cue to the index position, which was not convenient.

  The present invention has been proposed in view of such a conventional situation, and information processing that automatically extracts and integrates a swell portion desired by a viewer from an audio signal or reproduces such a swell portion. An object is to provide a device and a portable terminal device.

  In order to achieve the above-described object, an information processing apparatus according to the present invention obtains a feature amount of an audio signal for each predetermined time interval in an information processing device that extracts an important part in an audio signal, and uses the feature amount. An importance determining means for determining the importance in the time interval based on the above, an extracting means for extracting the important part based on the importance, and an integrating means for integrating at least some of the extracted important parts; Is provided.

  Here, the information processing apparatus according to the present invention may further include an information transmission unit that transmits the information integrated by the integration unit to the outside.

  Such an information processing apparatus extracts an important part from, for example, an audio signal of a television broadcast, and integrates at least some of the extracted important parts.

  In order to achieve the above-described object, the mobile terminal device according to the present invention obtains a feature amount of an audio signal for each predetermined time interval, determines the importance in the time interval based on the feature amount, Communication means for communicating with an information processing apparatus that extracts and integrates important parts of the audio signal based on the importance, and reproducing means for reproducing the important parts.

  Such a portable terminal device receives an important part extracted from, for example, an audio signal of a television broadcast and integrated from the information processing apparatus, and reproduces the important part.

  In order to achieve the above-described problem, the mobile terminal device according to the present invention obtains a feature amount of the audio signal for each predetermined time interval in the mobile terminal device that extracts and reproduces an important part in the audio signal. , Importance level judging means for judging the importance level in the time interval based on the feature amount, extraction means for extracting the important part based on the importance level, and at least some of the extracted important parts. An integrating means for integrating and a reproducing means for reproducing the integrated information are provided.

  Such a portable terminal device extracts an important part from an audio signal of, for example, a television broadcast, and integrates and reproduces at least some of the extracted important parts.

  An information processing apparatus according to the present invention, in an information processing apparatus that extracts an important part in an audio signal, obtains a feature amount of the audio signal for each predetermined time interval, and determines the importance in the time interval based on the feature amount. Importance determining means for determining, extraction means for extracting the important part based on the importance, and integration means for integrating at least a part of the extracted plurality of important parts.

  Here, the information processing apparatus according to the present invention may further include an information transmission unit that transmits the information integrated by the integration unit to the outside.

  According to such an information processing apparatus, for example, an important part is extracted from an audio signal of a television broadcast, and at least some of the extracted important parts are integrated. The viewer can easily view the important part.

  Further, the mobile terminal device according to the present invention obtains a feature amount of an audio signal for each predetermined time interval, determines an importance level in the time interval based on the feature amount, and determines the audio signal based on the importance level. Communication means for communicating with an information processing apparatus that extracts and integrates the important part of the above and a reproducing means for reproducing the important part.

  According to such a mobile terminal device, for example, an important part extracted and integrated from an audio signal of a television broadcast is received from the information processing apparatus, and the user can easily view the important part by reproducing the important part. can do.

  Further, the mobile terminal device according to the present invention obtains a feature amount of the audio signal for each predetermined time interval in a mobile terminal device that extracts and reproduces an important part in the audio signal, and the time based on the feature amount. Importance determination means for determining the importance in the section, extraction means for extracting the important part based on the importance, integration means for integrating at least some of the extracted important parts, and the integrated And reproducing means for reproducing the received information.

  According to such a portable terminal device, for example, an important part is extracted from an audio signal of a television broadcast, and at least some of the extracted important parts are integrated and reproduced. Can watch.

It is a figure which shows an example of the viewing-and-listening form of TV broadcast. It is a figure which shows the other example of the connection form between a broadcasting station and a telephone station. It is a figure which shows the other example of the connection form between a broadcasting station and a telephone station. It is a figure which shows the other example of the connection form between a broadcasting station and a telephone station. It is a figure which shows the conceptual structure of the information provision apparatus in 1st Embodiment. It is a flowchart explaining the process sequence of the importance determination part of the information provision apparatus. It is a figure which shows the example in the case of calculating | requiring the frequency intensity distribution of an audio | voice signal for every flame | frame of a video signal. It is a figure which shows the example in the case of utilizing also the frequency analysis result of the audio | voice signal corresponding to the flame | frame before and behind the present time. It is a figure which shows the usage example of the frequency analysis result of the frame before and behind. It is a figure which shows the extraction area in the extraction part of the information provision apparatus. It is a figure which shows an example of the transmission form from the transmission part of the information provision apparatus. It is a figure which shows an example of the transmission form from the transmission part of the information provision apparatus. It is a figure which shows an example of the transmission form from the transmission part of the information provision apparatus. It is a figure which shows the detailed structural example of the information provision apparatus in 1st Embodiment. It is a figure which shows the internal structure of the excitement area process part in the information provision apparatus. It is a flowchart explaining transmission / reception of the data between the portable terminal device and information provision apparatus in 2nd Embodiment. It is a figure which shows an example of the important information list produced with the information provision apparatus. It is a figure which shows the example of a display in the portable terminal device which received the important information list. It is a figure which shows the detailed structural example of the portable terminal device in 2nd Embodiment. It is a figure which shows the detailed structural example of the portable terminal device in 3rd Embodiment. It is a figure which shows the internal structure of the excitement area process part in the same information processing apparatus.

  Hereinafter, specific embodiments to which the present invention is applied will be described in detail with reference to the drawings. In this embodiment, an information processing apparatus and a mobile terminal apparatus according to the present invention extract an important part from a video / audio signal and integrate them to provide a viewer with information, and reproduce such information. Or applied to a portable terminal device that extracts and integrates important parts from video / audio signals. In the following embodiment, a television (hereinafter referred to as TV) broadcast will be described as an example of the video / audio signal.

  First, before explaining the information providing apparatus according to the first embodiment, FIG. The TV broadcast is transmitted by radio waves from the broadcast station 1, and the telephone company 2 receives it via an antenna. Then, the telephone company 2 processes the TV program that is the received information and sends it to a viewer, for example, a user of the receiving terminal 3 such as a mobile phone. Here, in FIG. 1, the broadcasting station 1 and the telephone company 2 are in the form of normal TV broadcasting. However, the present invention is not limited to this, and the broadcasting station 1 and the telephone are connected by a dedicated line as shown in FIG. The form of connecting with the company 2 may be the form of connecting with a network such as the Internet as shown in FIG. 3, or the form of connecting using satellite communication as shown in FIG. Further, it is not limited to the telephone company that finally provides information to the user, but may be a company or an individual other than the telephone company, or the broadcasting station itself. Hereinafter, a company or an individual that processes and provides information to a viewer in this manner is defined as an information provider, and a device that performs such processing is defined as an information providing device.

  The information provider processes the received TV program into a form desired by the viewer. For example, in the case of a sport program, the viewer wants to see all of the matches, but there are many cases where there is not enough time to see all of them or simply wants to watch multiple matches. Often you want to see only the parts that are advantageous or unfavorable to the teams and players you support. In such a scene with a score, the audience at the venue where the sport is held is also highly interested, and this will also appear specifically in the sound within the venue. In other words, the sound distribution “Wow” appears acoustically as an audience response. Moreover, since it is very rare that the venue changes or moves during the match, the acoustic characteristics at the venue are considered to be almost the same, and as a result, the audience's reaction shows the same tendency. In other words, the frequency distribution shows almost the same characteristics in the swelled part such as a scored scene.

  Therefore, in the present embodiment, this characteristic is used, a part where the frequency distribution shows the above characteristic is determined as a rising part, and the rising part is extracted as an important part. Note that since audio and video are synchronized in TV broadcasting, the corresponding video is also extracted in the same manner because the importance is high. At this time, if only the portion is not extracted but is extracted within the adjustable range, for example, the scenes before and after the score in the game can be extracted very accurately.

  FIG. 5 shows a conceptual configuration of an information providing apparatus that extracts important parts and provides them to viewers. As shown in FIG. 5, the information providing apparatus 10 includes an importance determination unit 11 that determines a part having high importance from the frequency distribution of the audio signal, an extraction unit 12 that extracts the important part, and the extracted information is recorded. The recording unit 13, the integration unit 14 that integrates these important parts, and the transmission unit 15 that transmits the integrated information to the viewer.

  Here, when receiving the TV broadcast, the importance determination unit 11 first checks the frequency intensity distribution of the audio signal for each predetermined time interval. Then, the frequency intensity distribution is matched with a frequency intensity distribution registered in advance as an important pattern, and for example, a part having a similarity equal to or greater than a threshold is determined as an important part.

  That is, as shown in the flowchart of FIG. 6, first, in step S1, a frequency intensity distribution is obtained for each predetermined time interval, and in step S2, whether or not the frequency intensity distribution matches a pre-registered important pattern. Is determined. If they match in step S2 (Yes), it is determined as an important part in step S3, and if not (No), the process proceeds to step S4. In step S4, it is determined whether or not the signal (program) is at the end. If it is the last (Yes), the importance determination process is terminated. If not (No), the process returns to step S1 to determine the determination. Continue.

  Here, the time interval for obtaining the frequency intensity distribution may be, for example, every 1 to several seconds, or may be every video frame. When obtaining the frequency intensity distribution for each frame, as shown in FIG. 7, frequency analysis is performed by using the audio signal corresponding to the frame of the current time “01:20:14” as a selected region to obtain the frequency intensity distribution. At this time, not only the audio signal corresponding to the frame but also the analysis result of the audio signal corresponding to the preceding and succeeding frames as shown in FIG. 8 can be used to improve the matching accuracy. In this case, as shown in FIG. 9, a weighting coefficient having a shoulder centered on the current time is multiplied for each frequency component, and these are added to correspond to the frame of the current time “01:20:14”. The frequency analysis result of the audio signal can be used.

  It should be noted that by making the thresholds adjustable during matching, various judgments can be made, such as when the values need to match closely or when they need to be somewhat similar. In an ambiguous match search, an ambiguous search using fuzzy or other techniques can be used. In addition to the registered pattern, a learning function may be provided, and a pattern learned from the registered pattern may be used as a matching template.

  The extraction unit 12 extracts the video / audio of the part determined to be important by the importance determination unit 11, copies the part, and records it in the recording unit 13 separately from the original video / audio signal. At this time, it is preferable to extract not only that part but also within the adjustable range. That is, for example, as shown in FIG. 10, when it is determined that the section corresponding to the frame at time “01:20:14” is important, the sections corresponding to the frames before and after that are also extracted. This range can be set, for example, 3 minutes before and after the important part. Furthermore, by making this range changeable, it can be changed according to the program to be viewed, and convenience is enhanced.

  Further, the extraction unit 12 may not extract the important part at the time when the video is flowing, and may record only the start point and end point markers that the part is important in the recording unit 13. . Also in this case, it is preferable to include before and after the important part. The marker may be embedded or added to the original video / audio signal. However, if the signal itself is not desired to be changed, it can be recorded in the recording unit 13 as a database separately from the signal. However, for example, in the case of a video signal, it is necessary to make it easy to know which part of the original signal corresponds to, for example, using position information such as TBC (Time Base Corrector) possessed by the signal. It is.

  The integration unit 14 integrates the important parts recorded in the recording unit 13 in, for example, chronological order. At this time, you may make it add the header information which demonstrates the outline | summary between each important part. Moreover, you may make it replace and integrate in arbitrary orders, without following a time series.

  The transmission unit 15 receives the important part integrated by the integration unit 14 as a viewer, for example, a mobile terminal device such as a mobile phone or a PDA (Personal Digital Assistance), or a receiving terminal 3 including a TV receiver, a PC (Personal Computer), or the like. Call to other users. As a transmission method, the transmission side may make a transmission at an arbitrary time, or the viewer side may make a transmission request at an arbitrary time and make a transmission from the transmission side accordingly. In the latter case, the viewer can watch at the time and place desired by the viewer. Further, the transmission form may be a transmission using a general network such as the Internet or a dedicated line as shown in FIG. 11, and a transmission using satellite communication as shown in FIG. You may do. Further, when the broadcast station itself extracts the important part, as shown in FIG. 13, it may be transmitted from the broadcast station in the same manner as the conventional TV broadcast.

  FIG. 14 shows a detailed configuration example of the information providing apparatus 10 described above. As shown in FIG. 14, the information providing apparatus 10 includes a central processing unit (CPU) 100 that controls each unit of the information providing apparatus 10, a read only memory (ROM) 101 that is a nonvolatile memory, A RAM (Random Access Memory) 102 that is a volatile memory, a so-called TV tuner, for example, a video / audio data communication unit 103 that receives a TV broadcast from a broadcasting station, and a climax that detects a climax section as described above. The section processing unit 104 and a communication circuit 105 that communicates via a network such as the Internet, a dedicated line, or satellite communication are connected via a control line 110 and a data line 120.

  In such an information providing apparatus 10, the CPU 100 performs control for executing the program in accordance with, for example, a program recorded in the ROM 101. The RAM 102 temporarily stores programs and data necessary for the CPU 100 to execute various processes as necessary.

  The video / audio data communication unit 103 stores the video / audio signal received via the antenna 106 in the RAM 102, and the RAM 102 buffers this signal for a certain period of time and then sequentially outputs it to the upswing section processing unit 104. Of course, the data may be stored not in the RAM 102 but in an external storage device (not shown) such as a memory card.

  For example, as shown in FIG. 15, the climax section processing unit 104 includes a spectrum conversion unit 150 that performs spectrum conversion of a signal on the time axis input via the data line 120 to a signal on the frequency axis, and an important registered in advance. An important pattern storage unit 151 that stores patterns, a determination unit 152 that determines whether or not data is a climax section for each time interval, an extraction unit 153 that extracts a climax segment, and each climax segment are integrated. The integration unit 154 and a data control unit 155 that controls the climax section processing unit 104 in an integrated manner.

  The spectrum conversion unit 150 converts the input signal on the time axis into a frequency spectrum by FFT (Fast Fourier Transform) or the like for each predetermined time interval described above to obtain a frequency intensity distribution. Then, the determination unit 152 determines the importance by comparing the frequency intensity distribution read from the important pattern storage unit 151 and the frequency intensity distribution obtained by the spectrum conversion. The data control unit 155 is notified.

  When the data control unit 155 receives the notification from the determination unit 152, the data control unit 155 activates the extraction unit 153, and the extraction unit 153 reads the signal before the important part from the RAM 102 (FIG. 14), and the signal of the important part and the subsequent signal. To the integration unit 154. The integrating unit 154 sequentially stores the signals sent from the extracting unit 153 and integrates them as one signal.

  Returning to FIG. 14, the communication circuit 105 transmits the signal integrated by the integration unit 154 (FIG. 15) to the viewer at an arbitrary time or in response to a transmission request from the viewer.

  As described above, according to the first embodiment, the information providing apparatus 10 checks the frequency intensity distribution of the audio signal for each predetermined time interval, and matches the frequency intensity distribution with a pre-registered important pattern. By doing so, it is possible to automatically extract and integrate the important part (swelling part) required by the viewer from the TV broadcast, and to easily provide the important part to the viewer. In addition, the viewer can easily view the important part without performing cueing or the like.

  Next, in the second embodiment described below, the information providing apparatus 10 does not transmit all of the integrated important parts to the viewer as in the first embodiment. The list information is created and transmitted to the mobile terminal device 20 of the viewer, and the viewer downloads only desired information from the important parts.

  That is, as shown in the flowchart of FIG. 16, when the user of the portable terminal device 20 first requests a list of important parts, for example, a list of scoring scenes of team A versus team B in step S10, in step S11, the information providing apparatus 10 The list information as shown in FIG. 17 is transmitted to the mobile terminal device 20. Thereby, a screen as shown in FIG. 18 is displayed on the display unit of the mobile terminal device 20.

  Next, when the user of the mobile terminal device 20 checks the check box for the desired scoring scene in the list information shown in FIG. 18, and selects the button “Receive selection unit”, the mobile phone in step S12. The terminal device 20 requests the information providing device 10 to transmit the selected part.

  Subsequently, when the information providing apparatus 10 transmits one of the selected portions in step S13, the portable terminal device 20 stores or reproduces the received selected portion in step S14. When the information providing apparatus 10 transmits the last selected portion in step S15, the portable terminal apparatus 20 transmits an end notification to the information providing apparatus 10 in step S16.

  Note that in the case of the mobile terminal device 20 that performs ACK notification transmission, when one of the selected portions is received, an acknowledgment indicating that it has been received normally is returned to the information providing device 10, and the mobile terminal device 20 has failed to receive normally. Returns an acknowledgment indicating that the reception has failed to the information providing apparatus 10.

  FIG. 19 shows a detailed configuration example of the mobile terminal device 20 that performs such processing. As shown in FIG. 19, the mobile terminal device 20 includes a CPU 200 that controls each part of the mobile terminal device 20, a ROM 201 that is a nonvolatile memory, a RAM 202 that is a volatile memory, and a display unit 206. A display control unit 203 that controls display of video on the display unit, a data reproduction unit 204 that performs processing for reproducing information stored in the RAM 202 so that the information can be displayed on the display unit 206, and a communication circuit 205 that communicates via a network such as the Internet. Are connected via a control line 220 and a data line 230. Furthermore, a numeric keypad 207 as an input means is connected to the control line 220, and a speaker 208 that outputs sound and a microphone 209 that collects sound are connected to the data line 230.

  In such a portable terminal device 20, the CPU 200 performs control for executing the program according to the program recorded in the ROM 201, for example. The RAM 202 temporarily stores programs and data necessary for the CPU 200 to execute various processes as necessary.

  The communication circuit 205 communicates with the information providing apparatus 10 via the antenna 210, and receives the important information list described above, information selected from the list, and the like. The communication circuit 205 stores the received information in the RAM 202. Of course, the data may be stored not in the RAM 202 but in an external storage device (not shown) such as a memory card.

  The data reproducing unit 204 performs processing for reproducing data such as the important information list and the selected important information stored in the RAM 202 so that the data can be displayed on the display unit 206.

  As described above, according to the second embodiment, the list information of the important part (swelling part) extracted in the information providing apparatus 10 is created and transmitted to the mobile terminal device 20 of the viewer, and the mobile terminal device When the viewer designates and downloads only desired information from the important portions at 20, the viewer can easily view only the portion selected by the viewer.

  Subsequently, in the third embodiment described below, the important part is extracted from the TV broadcast received by the mobile terminal device itself without using the information providing device 10 as in the first and second embodiments. Integrate and replay the critical parts that are integrated.

  FIG. 20 shows a detailed configuration example of the mobile terminal device 30 that performs such processing. As shown in FIG. 20, the mobile terminal device 30 includes a CPU 300 that controls each part of the mobile terminal device 30, a ROM 301 that is a nonvolatile memory, a RAM 302 that is a volatile memory, and a so-called TV tuner. For example, a video / audio data communication unit 303 that receives a TV broadcast from a broadcasting station, a climax section processing unit 304 that detects a climax section as described above, and display control that controls display of video on the display unit 308. The control line 320 and the data line 330 include a unit 305, a data reproduction unit 306 that performs processing for reproducing information stored in the RAM 302 so that the information can be displayed on the display unit 308, and a communication circuit 307 that communicates via a network such as the Internet. And connected through. Further, a numeric keypad 309 as input means is connected to the control line 320, and a speaker 310 that outputs sound and a microphone 311 that collects sound are connected to the data line 330.

  In such a portable terminal device 30, the CPU 300 performs control for executing the program in accordance with, for example, a program recorded in the ROM 301. In the RAM 302, programs and data necessary for the CPU 300 to execute various processes are temporarily stored as necessary.

  The video / audio data communication unit 303 stores the video / audio signal received via the antenna 312 in the RAM 302, and the RAM 302 buffers this signal for a certain period of time and then sequentially outputs it to the upsurge section processing unit 304. Of course, the data may be stored not in the RAM 302 but in an external storage device (not shown) such as a memory card.

  For example, as shown in FIG. 21, the climax section processing unit 304 stores a spectrum conversion unit 350 that performs spectrum conversion of a signal on the time axis input via the data line 330 into a signal on the frequency axis, and stores important patterns. An important pattern storage unit 351, a determination unit 352 that determines whether or not the data is a climax section for each time interval, an extraction unit 353 that extracts the climax segment, and an integration unit 354 that integrates the climax segments. And a data control unit 355 that controls the climax section processing unit 304 in an integrated manner.

  The spectrum conversion unit 350 converts the input signal on the time axis into a frequency spectrum by FFT or the like for each predetermined time interval described above to obtain a frequency intensity distribution. The determination unit 352 determines the importance by comparing the frequency intensity distribution read from the important pattern storage unit 351 with the frequency intensity distribution obtained by the spectrum conversion, and if it is determined to be important, the determination is made. The data control unit 355 is notified. Note that the important pattern stored in the important pattern storage unit 351 may be a default pattern or a pattern arbitrarily created by the user. Also, it may be downloaded from a broadcasting station that broadcasts a program via the antenna 313 of the communication circuit 307 before the program is broadcast, or may be purchased from a predetermined site.

  When the data control unit 355 receives the notification from the determination unit 352, the data control unit 355 activates the extraction unit 353, and the extraction unit 353 reads the signal before the important part from the RAM 302 (FIG. 20), and the signal of the important part and the subsequent signal. To the integration unit 354. The integrating unit 354 sequentially stores the signals sent from the extracting unit 353 and integrates them as one signal.

  Returning to FIG. 20, the data reproduction unit 306 reads out the signal integrated by the integration unit 354 (FIG. 21), for example, in response to a reproduction request from the user, and performs a process of reproducing the signal so that the display unit 308 can display it.

  As described above, according to the third embodiment, the portable terminal device 30 examines the frequency intensity distribution of the audio signal for each predetermined time interval, and matches the frequency intensity distribution with the important pattern. It is possible to automatically extract and integrate important parts (swelling parts) required by the user from the TV broadcast, so that the important parts can be easily viewed.

  It should be noted that the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the scope of the present invention.

  For example, in the above-described embodiment, it has been described that it is determined whether or not it is an important part based on an audio signal of TV broadcast, and the audio and video of the important part are extracted. However, the present invention is not limited to this. For example, in the case of radio broadcasting, the same effect can be obtained by extracting only the audio signal of the important part.

  As described above in detail, the information processing apparatus according to the present invention obtains the feature amount of the sound signal for each predetermined time interval in the information processing device that extracts an important part in the sound signal, and based on the feature amount. Importance determining means for determining importance in the time interval, extraction means for extracting the important part based on the importance, and integration means for integrating at least some of the extracted important parts. It is to be prepared.

  Here, the information processing apparatus according to the present invention may further include an information transmission unit that transmits the information integrated by the integration unit to the outside.

  According to such an information processing apparatus, for example, an important part is extracted from an audio signal of a television broadcast, and at least some of the extracted important parts are integrated. The viewer can easily view the important part.

  Further, the mobile terminal device according to the present invention obtains a feature amount of an audio signal for each predetermined time interval, determines an importance level in the time interval based on the feature amount, and determines the audio signal based on the importance level. Communication means for communicating with an information processing apparatus that extracts and integrates the important part of the above and a reproducing means for reproducing the important part.

  According to such a mobile terminal device, for example, an important part extracted and integrated from an audio signal of a television broadcast is received from the information processing apparatus, and the user can easily view the important part by reproducing the important part. can do.

  Further, the mobile terminal device according to the present invention obtains a feature amount of the audio signal for each predetermined time interval in a mobile terminal device that extracts and reproduces an important part in the audio signal, and the time based on the feature amount. Importance determination means for determining the importance in the section, extraction means for extracting the important part based on the importance, integration means for integrating at least some of the extracted important parts, and the integrated And reproducing means for reproducing the received information.

  According to such a portable terminal device, for example, an important part is extracted from an audio signal of a television broadcast, and at least some of the extracted important parts are integrated and reproduced. Can watch.

  DESCRIPTION OF SYMBOLS 1 Broadcasting station, 2 Telephone company, 3 Receiving terminal, 10 Information provision apparatus, 11 Importance judgment part, 12 Extraction part, 13 Recording part, 14 Integration part, 15 Transmission part, 20 Portable terminal device, 103,303 Video / audio Data communication unit, 104, 304 Exciting section processing unit, 105, 205, 307 Communication circuit, 203 Display control unit, 204, 306 Data reproduction unit, 206, 308 Display unit, 207 Numeric keypad, 208, 310 Speaker

Claims (16)

In an information processing apparatus that extracts an important part in an audio signal,
Importance level judging means for obtaining a feature amount of the audio signal for each predetermined time interval and determining the importance level in the time interval based on the feature amount;
Extraction means for extracting the important part based on the importance,
An information processing apparatus comprising: integration means for integrating at least a part of the extracted plurality of important parts.   The information processing apparatus according to claim 1, further comprising: an information transmission unit that transmits the information integrated by the integration unit to the outside.   The information processing apparatus according to claim 1, wherein the importance level determination unit determines the importance level based on a frequency intensity distribution of the audio signal for each time interval.   4. The information according to claim 3, wherein the importance level determination means determines the importance level by comparing the frequency intensity distribution obtained for each time interval with a frequency intensity distribution of an important part registered in advance. Processing equipment. The audio signal is accompanied by a video signal,
The information processing apparatus according to claim 1, wherein the extraction unit extracts the important part and the video signal at a time corresponding to the important part.   The information processing apparatus according to claim 1, wherein the extraction unit extracts the important part and a signal within a predetermined time before and after the important part.   The information processing apparatus according to claim 1, wherein the integration unit integrates the plurality of important parts in a time-series order or an arbitrary order.   The information processing apparatus according to claim 2, wherein the transmission unit transmits the integrated information in response to an external request.   The information processing apparatus according to claim 2, wherein the transmission unit transmits the integrated information to an outside at an arbitrary time. A storage means for storing the important part;
The information processing apparatus according to claim 1, wherein the extraction unit stores a copy of the important part in the storage unit. A storage means for storing the extracted important part;
The extraction means stores information on the start point and end point of the important part in the storage means,
The information processing apparatus according to claim 1, wherein the integration unit integrates the important parts based on information on the start point and end point stored in the storage unit. Information processing for obtaining a feature amount of a speech signal for each predetermined time interval, determining an importance level in the time interval based on the feature amount, and extracting and integrating important portions in the speech signal based on the importance level Communication means for communicating with the device;
A portable terminal device comprising: reproducing means for reproducing the important part. The communication means receives the list information of the important part from the information processing apparatus, transmits designation information for specifying a desired part of the list information to the information processing apparatus,
The portable terminal device according to claim 12, wherein the reproduction means reproduces the desired portion transmitted from the information processing apparatus in accordance with the designation information.   The important part is extracted based on the importance by comparing the frequency intensity distribution of the audio signal for each time interval with the frequency intensity distribution of the important part registered in advance. The information processing apparatus according to claim 12. The audio signal is accompanied by a video signal,
The portable terminal device according to claim 12, wherein the reproduction means reproduces the important part and the video signal at a time corresponding to the important part. In a portable terminal device that extracts and reproduces an important part in an audio signal,
Importance level judging means for obtaining a feature amount of the audio signal for each predetermined time interval and determining the importance level in the time interval based on the feature amount;
Extraction means for extracting the important part based on the importance,
An integration means for integrating at least some of the extracted plurality of important parts;
A portable terminal device comprising: reproduction means for reproducing the integrated information.

Images