JP2010166123A - Apparatus and method for processing information and program - Google Patents

Abstract

Meta information including the name of a song can be set for a section in the recorded content in which the song is played.
CM music information is acquired from a CM music information distribution server 3 based on CM broadcast start time and broadcast station information. The song name acquired from the CM song information distribution server 3 is stored in association with the feature amount of the CM audio information. When a program including a section in which a song is played, such as a music program, is recorded and the feature amount of audio information in each section of the music clip is extracted, a matching search is performed. When a section in a music clip from which the feature value of the voice information whose degree of coincidence with the feature value of the CM's voice information is equal to or greater than the threshold is identified, the name of the song used in the CM is used as meta information Set to music clip. The present invention can be applied to a device having a recording function.
[Selection] Figure 9

Description

  The present invention relates to an information processing apparatus, an information processing method, and a program, and in particular, can set meta information including the name of a song for a section in which recorded music is included, included in recorded content. The present invention relates to an information processing apparatus, an information processing method, and a program that can be performed.

  In recent years, recording devices such as hard disk recorders and Blu-ray (trademark) recorders have become widespread.

  As a recording device, after recording a music program in which multiple artists perform in order, chapters are set at the start and end positions of each artist's performance section, making it easy to play back the section of your favorite artist It has been done to be able to do it. Many recording devices sold in recent years are equipped with a function that allows a user to set a chapter at a predetermined position of a recorded program by operating a remote controller or the like.

  In other words, the section of the music program divided by chapters becomes music content with video. Music content with video is also called a music clip.

  You can select your favorite music clips from multiple music clips from a single music program and record them on the optical disc, or transfer them to a portable music player for viewing on the go. It has been broken.

  By the way, conventionally, there is a service called “eMarker” (trademark) (Non-Patent Document 1).

  “EMarker” is a service realized using a portable dedicated terminal. A button is provided on the surface of the dedicated terminal, and a memory for storing time information and the like is provided therein.

  When the user presses a button on the dedicated terminal when he / she wants to know the name of a song listened to on a radio program or television program, information such as the time zone when the user presses the button is recorded in the memory in the terminal. After that, when the dedicated terminal is connected to the personal computer, the name of the song that was heard when the button was pressed and the information of the CM that uses the song as BGM are searched on the server, and the information is stored in the personal computer. Displayed on the screen. The user can check who is singing a CM (Commercial Message) song of interest.

JP 2007-124777 A “Bookmarked songs and commercials that I was interested in on radio and TV. New service“ eMarker ”, service started in the Tokyo metropolitan area”, search on December 22, 2008, <URL: http://www.sony.co .jp / SonyInfo / News / Press_Archive / 200012 / 00-061b />

  When selecting the music clip to be recorded on the optical disc or transferred to the music player, if the song name of each music clip is displayed, it is convenient to select the music clip based on the song name. .

  Conventionally, program names are automatically set as meta information based on EPG (Electronic Program Guide) data for recorded programs, but information different from the program name is given to music clips that are one section of the entire program. It is difficult to set it automatically as meta information.

  For example, if the same name as the name of a music program is set for a music clip, the same name is set for all music clips generated based on the same music program, so select the music clip. Difficult to understand when doing.

  It is troublesome for the user to manually set meta information such as the song name by checking the contents of the music clip and operating the remote controller or keyboard.

  The present invention has been made in view of such a situation, and it is possible to set meta information including the name of a song for a section where the song is reproduced, which is included in the recorded content. It is to make.

  An information processing apparatus according to one aspect of the present invention includes an acquisition unit that acquires CM song information that is information including the name of a song used in a CM, a feature amount of audio information of a recorded CM, and a recorded Extraction means for extracting the feature amount of the audio information of the section in which the song is played, included in the content, and the feature amount of the voice information of the recorded CM in the section in which the song is played back A setting unit configured to set information included in the CM music information as meta information of a section in which the music is played when the section in which the feature amount of the voice information whose degree is equal to or greater than the threshold is included .

  The acquisition means causes the CM providing time and the CM music information to be managed in association with each other via a network, and the CM managed in association with the recorded CM providing time. Song information can be acquired.

  When presenting a section in which the music is played, display control means for displaying the name of the music included in the meta information set by the setting means can be further provided.

  A playback unit is further provided that plays back a section in which a feature amount of voice information having a degree of coincidence with a feature amount of voice information of the recorded CM is extracted from a whole section in which the music is played. Can do.

  An information processing method or program according to one aspect of the present invention acquires CM song information, which is information including the name of a song used in a CM, and features audio information features of recorded CM and recorded content. And the feature amount of the audio information of the section in which the song is reproduced is extracted, and the degree of coincidence with the feature amount of the recorded audio information in the section in which the song is reproduced is equal to or greater than a threshold value If the section from which the feature amount of the audio information is extracted is included, the step includes setting the information included in the CM song information as meta information of the section in which the song is played.

  In one aspect of the present invention, CM song information, which is information including the name of the song used in the CM, is acquired, and the feature amount of the audio information of the recorded CM and the song included in the recorded content And the feature amount of the audio information in the section where the reproduction is performed. In addition, when the section in which the song is played includes a section in which the feature amount of the voice information whose degree of coincidence with the feature amount of the voice information of the recorded CM is equal to or greater than a threshold value, Information included in the CM music information is set as meta information of a section in which reproduction is performed.

  According to one aspect of the present invention, meta information including the name of a song can be set for a section in which the song is played, which is included in the recorded content.

It is a block diagram which shows the structural example of the communication system which concerns on one Embodiment of this invention. It is a figure which shows the example of the information managed in CM music information delivery server. It is a figure which shows the example of operation | movement of the video recording / reproducing apparatus which acquires CM music information. It is a figure which shows the example of CM music information and a feature-value. It is a figure which shows the example of a music clip. It is a figure which shows the example of the feature-value of the audio | voice information of a music clip. It is a figure which shows the example of a coincidence search. It is a figure which shows the example of the meta information of a music clip. It is a figure which shows a series of flows until it sets the meta information of a music clip. It is a figure which shows the example of the list screen of a music clip. It is a block diagram which shows the structural example of a video recording / reproducing apparatus. It is a flowchart explaining the recording process of a recording / reproducing apparatus. It is a flowchart explaining the CM music information acquisition process of a recording / reproducing apparatus. It is a flowchart explaining the meta information setting process of a recording / reproducing apparatus. It is a flowchart explaining the reproduction | regeneration processing of a video recording / reproducing apparatus. It is a figure which shows the example of the reproduction | regeneration area of a music clip. It is a block diagram which shows the structural example of another communication system. It is a figure which shows a series of flows until it sets meta information. It is a block diagram which shows the structural example of a computer.

[System configuration and operation]
FIG. 1 is a block diagram illustrating a configuration example of a communication system according to an embodiment of the present invention.

  As shown in FIG. 1, this communication system is configured by connecting a recording / playback apparatus 1 and a CM music information distribution server 3 via a network 2 such as the Internet.

  The recording / playback apparatus 1 is a device such as a hard disk recorder or a Blu-ray recorder. A television receiver is connected to the recording / playback apparatus 1 via a cable. In addition to the recording / playback function, the recording / playback apparatus 1 has a function of communicating with the CM music information distribution server 3 via the network 2.

  The CM music information distribution server 3 has the same function as the server that provides the above-described “eMarker” service. Based on the time information transmitted via the network 2, the CM song information distribution server 3 stores information on the songs used in the CM provided by the television broadcast in the time zone including the time. The time information is transmitted to the device that has transmitted the time information.

  FIG. 2 is a diagram illustrating an example of information managed in the CM music information distribution server 3.

  As shown in FIG. 2, information such as the broadcast start time, the name of a song used as BGM (Back Ground Music), and the name of an artist performing the song are associated with each CM and managed. Note that the CM includes video and audio for promoting programs and events in addition to video and audio for promoting products and services.

  In the example of FIG. 2, broadcast start time “12:00:00” (12:00:00), song name “AAA”, and artist name “aaa” are associated with CM1. For CM2, broadcast start time “12:00:15”, song name “BBB”, and artist name “bbb” are associated.

  For CM3, the broadcast start time “12:00:30”, the song name “CCC”, and the artist name “ccc” are linked. For CM4, the broadcast start time “12:00:45”, the song title “DDD” and artist name “ddd” are linked.

  Not only the time information but also the information of the channel on which each CM is broadcast may be linked and managed. Hereinafter, information such as the name of the song and the artist name used in the CM as BGM will be referred to as CM song information.

  Returning to the description of FIG. 1, the recording / playback apparatus 1 communicates with the CM song information distribution server 3 that manages such CM song information, and is included in the CM song information acquired from the CM song information distribution server 3. Set the information to be recorded as meta information of the music clip.

  The music clip is music content with video as described above. In the recording / playback apparatus 1, a section in which a song is played back together with video included in recorded content such as a music program is managed as a music clip.

  For example, when the user instructs display of a list of music clips, information such as song names included in meta information of each music clip is displayed on the television receiver connected to the recording / playback apparatus 1. The user can select a music clip to be played on the recording / playback apparatus 1 or a music clip to be transferred from the recording / playback apparatus 1 to a portable music player while viewing the song title.

  FIG. 3 is a diagram showing an example of the operation of the recording / playback apparatus 1 for acquiring CM music information.

  In the example of FIG. 3, a variety program is recorded, and audio information and image information are analyzed, so that a section between the main part 1 and the main part 2 is detected as a CM section. The detected CM section is composed of CMs 1 to 4 which are four CMs.

  The broadcast start time of CM1 is “12:00:00”, and the broadcast start time of CM2 is “12:00:15”. The broadcast start time of CM3 is “12:00:30”, and the broadcast start time of CM4 is “12:00:45”.

  CM detection is that there is a scene change between the main part of the program and the CM, between CM and CM, the sound is stereo sound in the CM section, and one CM section is an integer multiple of 15 seconds This is based on the fact that it is a section of a length of. These characteristics of image information and audio information are extracted in the recording / playback apparatus 1. CM detection is described in, for example, Japanese Patent Application Laid-Open No. 2002-16873.

  In the recording / playback apparatus 1, an inquiry is made to the CM song information distribution server 3, and the CM song information of each CM is acquired based on the information of the detected broadcast start time of the CM.

  Since the broadcast start time of CM1 is “12:00:00”, the CM song information distribution server 3 assumes that CM1 in FIG. 3 is the same CM as CM1 in FIG. 2 based on the database as shown in FIG. Identified. “AAA” which is the name of the song used as BGM in CM 1 is transmitted from the CM song information distribution server 3 and acquired by the recording / playback apparatus 1.

  Similarly, CMs 2 to 4 in FIG. 3 are identified as the same CMs as CMs 2 to 4 in FIG. 2 based on the broadcast start time. In the example of FIG. 3, “BBB” is the name of the song used in CM2, “CCC” is the name of the song used in CM3, and “DDD” is the name of the song used in CM4. Is acquired.

  Further, in the recording / playback apparatus 1, the feature amount is extracted by analyzing the audio information of each CM, and is managed in association with the CM song information of each CM. Since the audio information of the CM includes the music used as BGM, the extracted feature quantity also represents the characteristics of the music used in the CM. For example, a feature quantity such as a power spectrum and a tempo indicating the distribution of components for each frequency band is extracted.

  FIG. 4 is a diagram illustrating an example of CM music information and feature amounts.

In the example of FIG. 4, “AAA”, which is the name of the song used in CM1, and “a ₁ ”, which is the value of feature amount 1 extracted from the voice information of CM1, are used as CM1 information. “A ₂ ” which is the value of the quantity 2 is stored in association with it.

In addition, as information of CM2, “BBB” which is the name of the song used in CM2, “b ₁ ” which is the value of feature 1 extracted from the audio information of CM2, and the value of feature 2 A certain “b ₂ ” is associated and stored. Similarly, the names of songs and the values of feature quantities 1 and 2 are stored in association with CMs 3 and 4.

  As described above, in the recording / playback apparatus 1, information such as the name of the song used in the CM included in the recorded program is acquired as a pre-process for setting the meta information of the music clip, and the CM It is stored in association with the feature amount of the voice information. By performing such processing for all the recorded programs, the recording / playback apparatus 1 has information such as the names of songs used in various CMs and the feature amount of CM audio information. It will be associated and stored.

  Since information such as the name of the song used in the CM and the feature value of the CM's audio information are stored in association with each other, the CM data itself is not used to set meta information in the music clip. It may be deleted together with program data.

  FIG. 5 is a diagram illustrating an example of a music clip.

  The music program shown in FIG. 5 is, for example, a recorded program in which a plurality of artists perform in order, and by setting a chapter, the music program is divided into sections of songs 1 to 4 performed by each artist. ing. The sections of songs 1 to 4 are managed as music clips 1 to 4, respectively.

  In the recording / playback apparatus 1, for example, by setting chapters, music programs are divided and managed as music clips. The chapter start position and end position may be detected without setting chapters, and the section from the detected start position to end position may be managed as a music clip.

  The user can play back or transfer to a portable music player in units of music clips.

  Further, the recording / playback apparatus 1 analyzes the audio information of each music clip, and extracts feature quantities such as a power spectrum and a tempo in the same manner as the audio information of the CM. For example, the feature amount of the voice information for each section to be compared with the feature amount of the voice information of the CM, such as every section for 15 seconds, is extracted.

  FIG. 6 is a diagram illustrating an example of a feature amount of audio information of a music clip. Here, as the feature amount of each music clip, the feature amount extracted from the speech information of one section to be compared with the feature amount of the CM speech information is shown.

In the example of FIG. 6, “b ₁ ” that is the value of feature amount 1 and “b ₂ ” that is the value of feature amount 2 are stored in association with each other as the feature amount of the audio information of music clip 1. The music clip 1 includes a section of audio information in which the feature value 1 is “b ₁ ” and the feature value 2 is “b ₂ ”.

In addition, “e ₁ ” that is the value of the feature amount 1 and “e ₂ ” that is the value of the feature amount 2 are stored in association with each other as the feature amount of the audio information of the music clip 2. The music clip 2 includes a section of audio information in which the feature value 1 is “e ₁ ” and the feature value 2 is “e ₂ ”.

  Similarly, for the music clips 3 and 4, the value of the feature value 1 and the value of the feature value 2 extracted from the respective audio information are stored in association with each other. The feature amounts 1 and 2 in FIG. 6 are the same types of feature amounts as the feature amounts 1 and 2 in FIG.

  Thus, in the recording / playback apparatus 1, after the program is recorded, the feature amount of the audio information of each music clip is extracted and stored.

  FIG. 7 is a diagram illustrating an example of matching search.

  Information such as the name of the song used in the CM is stored in association with the feature amount of the voice information of the CM, and after the feature amount of the voice information of each music clip is stored, the recording / playback apparatus 1 has the feature. A quantity match search is performed. By the matching search, the section of the music clip from which the feature amount of the voice information whose degree of match with the feature amount of the voice information of the CM is equal to or greater than the threshold is specified.

  In the example of FIG. 7, the degree of coincidence between the feature amount of the voice information of CM1 and the feature amount of the voice information of each section of the music clips 1 to 4 is obtained. Each section indicated by the dotted lines in the music clips 1 to 4 is a target for obtaining the degree of coincidence with the feature amount of the voice information of CM1.

The value of feature amount 1 of the voice information of CM1 is “a ₁ ”, and the value of feature amount 2 is “a ₂ ” (FIG. 4). When feature quantities as shown in FIG. 6 have been extracted, hatched lines in FIG. 7 are used as sections in which feature quantities of voice information whose degree of coincidence with the feature quantity of voice information of CM1 is equal to or greater than a threshold. The section included in the music clip 4 shown is specified. As shown in FIG. 6, the music clip 4 includes a section of audio information in which the feature value 1 is “a ₁ ” and the feature value 2 is “a ₂ ”.

  When the section from which the feature amount of the voice information whose degree of coincidence with the feature amount of the voice information of CM1 is equal to or greater than the threshold is specified as the section of the music clip 4, the name of the song used in CM1 is “AAA "Is set as meta information of the music clip 4. In addition to the song name, information such as the artist name included in the CM song information is set as meta information.

  Similarly for other music clips, a matching search is performed based on the feature amount of the audio information, and information included in the CM song information is set as meta information.

  FIG. 8 is a diagram illustrating an example of music clip meta information.

  In the example of FIG. 8, the song name “AAA” is set as the meta information of the music clip 4 as described above.

Also, the song name “BBB” is set as meta information of the music clip 1. As shown in FIG. 6, the music clip 1 is content including a section of audio information in which the value of the feature value 1 is “b ₁ ” and the value of the feature value 2 is “b ₂ ”. In the example of FIG. 4, since the same value is extracted as the feature value value of the audio information of CM2, “BBB” which is the name of the song used in CM2 is set as the meta information of music clip 1 Will be.

  In the example of FIG. 8, the music title “EEE” is set for the music clip 2, and the music title “FFF” is set for the music clip 3.

  In this way, a match search is performed on the assumption that the same song as the song (music clip song) played in the music program is used in the CM, and the song is acquired from the CM song information distribution server 3. CM song information is set in the music clip as meta information.

  For example, an artist who plays a theme song of a movie as introduced in a commercial often appears in music programs and plays the theme song during the period before the release of a movie on which commercials are frequently broadcast. If the theme song is used as the BGM of a commercial for a movie, and the song name is registered in the CM song information distribution server 3, the music clip obtained from the music program in which the artist appears will contain CM song information. The title of the theme song acquired from the distribution server 3 is set.

  As described above, it is possible to set meta information including the name of a song for a music clip that is a section in which the song of the recorded content is reproduced.

  The part used in commercials is often the chorus part of the entire song. Assuming that the chorus part is used in the CM, the section in the music clip that is identified as the section from which the feature amount of the voice information that has a degree of coincidence with the feature amount of the voice information of the CM is extracted is It becomes the chorus part of the song played with the music clip. Information indicating the portion of the rust specified in this way may be set in the music clip as meta information.

  In the case of the example in FIG. 7, information indicating a section indicated by hatching is set as meta information of the music clip 4.

  FIG. 9 is a diagram showing a series of flows until the meta information of the music clip is set.

  When a predetermined program such as a variety program is recorded and a CM is detected, as shown as “1:” in FIG. 9, CM music information distribution is performed based on the CM broadcast start time and broadcast station information. CM music information is acquired from the server 3.

  In addition, the song title acquired from the CM song information distribution server 3 is stored in association with the feature amount of the CM audio information as indicated by “2:”.

  As shown as “3:”, when a program including a section in which a song is played, such as a music program, is recorded and the feature amount of audio information in each section of the music clip is extracted, “4: As shown in FIG.

  When a section in a music clip from which a feature value of voice information whose degree of coincidence with the feature value of the voice information of the CM is equal to or greater than a threshold is specified, it is used in the CM as shown as “5:”. The name of the current song is set in the music clip as meta information.

  The song name set as the meta information as described above is used, for example, when displaying a list of music clips.

  FIG. 10 is a diagram showing an example of a music clip list screen displayed on the television receiver connected to the recording / playback apparatus 1.

  The screen shown in FIG. 10 is displayed, for example, when the display of the music clip list screen is instructed from the menu screen displayed when the recording / playback apparatus 1 is activated.

  In the example of FIG. 10, “BBB”, “EEE”, “FFF”, and “AAA” are displayed as music titles of music clips in order from the top. “BBB”, “EEE”, “FFF”, and “AAA” are song names set as meta information of the music clips 1 to 4 as described with reference to FIG.

Thumbnail images S _{1 to} S ₄ are displayed on the left side of “BBB”, “EEE”, “FFF”, and “AAA”, respectively. The thumbnail images S _{1 to} S ₄ are, for example, the first frame image included in the image information of each music clip.

  The user can select a predetermined music clip by moving the cursor C up and down by operating the remote controller or the like while watching the displayed song title.

  After the music clip is selected, a menu related to the operation of the selected music clip is displayed on the screen. The user can instruct from the menu to transfer the music clip to the portable music player.

  When it is instructed to transfer the music clip to the portable music player, the meta information is also transferred together with the music clip data (image information, audio information) and stored in the memory inside the music player. Since the meta information is also transferred, the music clip title can be displayed on the screen of the music player.

[Configuration of recording device]
FIG. 11 is a block diagram illustrating a configuration example of the recording / playback apparatus 1.

  At least a part of the configuration shown in FIG. 11 is realized by a predetermined program being executed by a CPU (Central Processing Unit) included in the recording / playback apparatus 1.

  The broadcast receiving unit 11 receives a signal of a program broadcast by terrestrial digital broadcasting, BS (Broadcasting Satellite) broadcasting, CS (Communications Satellite) broadcasting, or the like based on a signal from an antenna (not shown). The broadcast receiving unit 11 performs various processes such as a decoding process on the received signal, and outputs a stream such as MPEG-TS to the program recording unit 12.

  The program recording unit 12 re-converts the stream supplied from the broadcast receiving unit 11 as it is or into an MPEG-4 format stream, and records it on a recording medium such as a hard disk. The stream recorded on the hard disk by the program recording unit 12 is read by the reproducing unit 24 as appropriate.

  The feature amount extraction unit 13 extracts the feature amount of the image information and audio information of each section of the recorded program, and outputs the feature amount to the feature amount holding unit 14, the CM section determination unit 15, and the music section determination unit 16.

  The feature amount holding unit 14 holds the feature amount extracted by the feature amount extraction unit 13 in association with a recorded program.

  The CM section determination unit 15 detects a CM included in a recorded program based on the feature amount extracted by the feature amount extraction unit 13, and uses the detected CM broadcast start time information as CM song information / feature amount. The data is output to the linking unit 19.

  Based on the feature amount extracted by the feature amount extraction unit 13, the music segment determination unit 16 detects a music segment, that is, a music clip that is a segment in which a song is played, and indicates the segment of each music clip. Information is output to the music section / feature value linking unit 20. When a plurality of songs are played in order, it is detected that the songs have been switched by the change in the feature value extracted by the feature value extraction unit 13.

  The section detected by the music section determination unit 16 includes not only a section in which a person is playing in a program but also a section in which music is reproduced along with a video such as a landscape. Further, not only a section from the beginning to the end of one song but also a section of one song is included.

  The network transmission / reception unit 17 acquires the CM song information associated with the broadcast start time and the broadcasting station by communicating with the CM song information distribution server 3 via the network 2, and uses the acquired CM song information as the CM song information. The data is output to the holding unit 18. Information such as the broadcast start time of each CM supplied from the feature amount holding unit 14 to the CM song information / feature amount association unit 19 is supplied from the CM song information / feature amount association unit 19.

  The CM song information holding unit 18 holds the CM song information acquired by the network transmission / reception unit 17 in the recording / playback apparatus 1 by recording it on the hard disk.

  The CM song information / feature amount linking unit 19 links the CM song information held by the CM song information holding unit 18 and the feature amount of the audio information held by the feature amount holding unit 14 for each CM. Manage. Information shown in FIG. 4 is managed by the CM song information / feature amount linking unit 19.

  The music section / feature amount linking unit 20 manages the music clip detected by the music section determination unit 16 and the feature amount of the audio information of the music clip held by the feature amount holding unit 14 in association with each other. Information shown in FIG. 6 is managed by the music section / feature amount linking unit 20.

  The coincidence search unit 21 includes the feature amount of the voice information of the CM managed by the CM song information / feature amount linking unit 19 and each section of the music clip managed by the music section / feature amount linking unit 20. A match search is performed based on the feature amount of the voice information. The match search unit 21 performs the processing as described with reference to FIG.

  When the match search unit 21 identifies the section of the music clip from which the feature value of the voice information whose degree of match with the feature value of the voice information of the CM is equal to or greater than the threshold value, -Obtained from the feature amount linking unit 19 and output to the meta information holding unit 22. In addition, the match search unit 21 stores music clip information including a section from which a feature amount of voice information whose degree of match with the feature amount of the voice information of the CM is equal to or greater than a threshold is the music section / feature amount linking unit 20. And output to the meta information holding unit 22.

  The meta information holding unit 22 sets the meta information in the music clip by managing the music clip information and the CM music information supplied from the match search unit 21 in association with each other. The meta information holding unit 22 manages information as shown in FIG.

  The meta information presentation unit 23 is appropriately set to a music clip by controlling a GUI (Graphical User Interface) on the screen of an external television receiver or controlling the display of the liquid crystal panel of the main body. Present meta information to the user. For example, a screen as shown in FIG. 10 is displayed by the meta information presentation unit 23.

  When the music clip to be played is selected by the user, the playing unit 24 reads and plays the data of the section of the music clip from the program data recorded by the program recording unit 12. Selection of a music clip to be played is performed from a screen as shown in FIG. The image and sound obtained by reproducing the music clip data are output from the television receiver.

[Recording and playback device processing]
Next, processing of the recording / playback apparatus 1 having the above configuration will be described.

  First, the processing of the recording / playback apparatus 1 for recording a program will be described with reference to the flowchart of FIG.

  In step S1, the broadcast receiving unit 11 receives a program that is to be recorded.

  In step S <b> 2, the program recording unit 12 records (records) the program received by the broadcast receiving unit 11.

  In step S3, the feature amount extraction unit 13 analyzes the image information and audio information of the recorded program, and uses the feature amount used for CM detection, the feature amount used for music clip detection, and the feature amount used for matching search. To extract.

  By repeatedly performing the above processing, the recording / playback apparatus 1 manages a program including a CM necessary for acquiring CM song information, a song that is managed as a music clip, and is a target for setting meta information. A program including a section in which playback is performed is recorded.

  Next, processing of the recording / playback apparatus 1 for acquiring CM music information will be described with reference to the flowchart of FIG.

  The process shown in FIG. 13 is performed after the feature quantity of the recorded program is extracted by performing the process of FIG.

  In step S11, the CM section determination unit 15 determines whether or not the CM has been recorded by performing CM detection based on the feature amount of the recorded program, and until it is determined that the CM has been recorded. stand by.

  If it is determined in step S11 that the CM has been recorded, in step S12, the network transmission / reception unit 17 acquires CM song information based on the CM broadcast start time. When the CM is recorded, information on the CM broadcast start time is output from the CM section determination unit 15 to the CM song information / feature amount linking unit 19 and supplied to the network transmission / reception unit 17.

  In step S13, the network transmission / reception unit 17 determines whether or not the CM music information has been acquired.

  When it is determined in step S13 that the CM song information has been acquired, in step S14, the CM song information / feature amount linking unit 19 links the CM song information and the feature amount of the CM audio information. Remember. The CM song information acquired by the network transmission / reception unit 17 is output to and held by the CM song information holding unit 18, and the CM song information and the feature amount of the voice information of the CM held by the feature amount holding unit 14 are stored. Is tied.

  After the feature values of the CM song information and the CM audio information are stored in association with each other in step S14, or when it is determined in step S13 that the CM song information could not be acquired, the processing after step S11 is performed. Repeated.

  Next, processing of the recording / playback apparatus 1 for setting meta information to a music clip will be described with reference to the flowchart of FIG.

  In step S21, the music section determination unit 16 determines whether or not a music clip has been detected based on the feature amount of a recorded program, and waits until it is determined that it has been detected.

  When it is determined in step S21 that the music clip has been detected, in step S22, the music section / feature value linking unit 20 stores the detected music clip and the feature value of the audio information of the music clip in a linked manner. To do.

  In step S23, the matching search unit 21 determines the feature amount of the audio information of the music clip based on the information managed by the CM song information / feature amount linking unit 19 and the music section / feature amount linking unit 20. Performs a match search for the feature amount of CM audio information.

  In step S24, the match search unit 21 extracts the segment of the music clip from which the feature amount of the voice information whose match degree with the feature amount of the voice information of the CM is equal to or greater than the threshold (matches the feature amount of the voice information of the CM). It is determined whether or not there is.

  If it is determined in step S24 that there is a section in which the feature value of the voice information that matches the feature value of the voice information of the CM is extracted, in step S25, the meta information holding unit 22 converts the information included in the CM song information into the meta information. Set to music clip as information and store. For a music clip including a section that matches the feature amount of the CM audio information, information such as a song name included in the CM song information of the CM is set as meta information.

  After the meta information is set in step S25, or when it is determined in step S24 that there is no music clip section that matches the feature amount of the CM audio information, the processes in and after step S21 are repeated.

  Next, processing of the recording / playback apparatus 1 for playing back music clips will be described with reference to the flowchart of FIG.

  In step S31, the meta information presenting unit 23 determines whether or not an instruction to display the meta information is given, and waits until it is determined that the display is instructed. For example, when the user gives an instruction to display a list of music clips, it is determined that an instruction to display meta information has been given.

  If it is determined in step S31 that the display of the meta information is instructed, in step S32, the meta information presenting unit 23 displays the meta information of each music clip held by the meta information holding unit 22. As a result, a screen as shown in FIG. 10 is displayed.

  In step S33, the playback unit 24 determines whether or not playback of a music clip has been instructed.

  When it is determined in step S33 that reproduction of a music clip has been instructed, in step S34, the reproduction unit 24 reads out and reproduces data in the section of the music clip from the program data recorded by the program recording unit 12.

  After the music clip is reproduced in step S34, or when it is determined in step S33 that the reproduction of the music clip is not instructed, the processes after step S31 are repeated.

  Through the above processing, the user can confirm information such as the name of a song reproduced in each music clip and select a music clip.

  FIG. 16 is a diagram illustrating an example of a music clip playback section.

When the information indicating the section from which the feature value of the audio information with the degree of coincidence with the feature value of the voice information of CM is set as the meta information of the music clip is set, it is not only from the beginning but only the section Playback may be performed. Positions p ₁ and p _{2 in} FIG. 16 are a start position and an end position of a section in which a feature amount of voice information whose degree of coincidence with the feature amount of CM voice information is equal to or greater than a threshold value.

  The section of the music clip from which the feature value of the voice information whose degree of coincidence with the feature value of the voice information of the CM is equal to or greater than the threshold is reproduced as the same part used in the CM of the entire song. It is a section. Since the portion used in the CM is often the chorus portion of the song as described above, the chorus portion of the entire music clip is thereby reproduced.

  By playing a plurality of music clips in a similar manner, the user can continuously watch the rust portion of each music clip.

  Playback is performed for a section in which a section of a music clip from which a feature amount of voice information having a degree of coincidence with a feature quantity of CM voice information as shown in FIG. You may do it.

For example, when the position of the scene change is detected by the feature amount extraction unit 13 as the feature amount of the image information, the scene change immediately after the position p ₂ from the position of the scene change immediately before the position p _{1 in} FIG. Up to the position of is played. Accordingly, it is possible to reproduce a section in which the reproduction of the video is performed in a natural manner while including the rust portion.

[Modification]
In the above, it is assumed that CM music information of CMs detected from recorded programs is acquired, but CM music information including those not recorded is downloaded from the CM music information distribution server 3 and recorded. You may make it record on the hard disk in the reproducing | regenerating apparatus 1. FIG. In this case, the CM song information associated with the feature amount of the audio information of the recorded CM is acquired from the hard disk in the recording / playback apparatus 1.

  In the above description, the case where the meta information is set to the music clip that is the section where the music is played back has been described. However, the meta information is added to the section where a certain performer appears in the recorded program. Similar processing can be applied to the setting.

  FIG. 17 is a block diagram illustrating a configuration example of a communication system in the case where meta information is set in a section in which a certain performer appears in a recorded program.

  The CM performer information distribution server 31 in FIG. 17 stores CM performer information, which is information such as the names of performers who appear in the CM. Based on the time information transmitted via the network 2, the CM performer information distribution server 31 obtains the CM performer information of the CM provided by the television broadcast in the time zone including the time, To the device that sent the information.

  With reference to FIG. 18, a series of flows performed in the recording / playback apparatus 1 to set meta information in a section in which a certain performer appears in a recorded program will be described.

  When the program 1, which is a predetermined program, is recorded and a CM is detected from the program 1, as shown as “1:” in FIG. 18, the program 1 is recorded based on the broadcast start time of the CM and broadcast station information. The name of the CM performer is acquired from the CM performer information distribution server 31.

  In addition, the name of the performer acquired from the CM performer information distribution server 31 is stored in association with the feature amount of the face of the performer appearing in the CM, as shown as “2:”. That is, in this example, not the voice information but the image information is analyzed, whereby the feature amount of the performer's face is extracted and stored in association with the CM performer information. As the face feature amount, for example, information such as the area of a predetermined portion such as an eye portion, a nose portion, and a mouth portion occupying the entire face, their positional relationship in the entire face, and the face color are extracted.

  As shown as “3:”, by analyzing the image information, the recorded program 2 is divided for each section in which the same performer is shown, and the characteristics of the face of the performer in each section are shown. When the amount is extracted, a matching search is performed as shown as “4:”.

  When the section in which the facial feature amount of the performer whose degree of coincidence with the facial feature amount of the CM performer is equal to or greater than the threshold is identified, the identified program 2 is indicated as “5:”. The name of the performer of the CM is set as meta information for the middle section.

  The performer name set as meta information as described above is used, for example, when displaying a list of sections in which the same performer is shown.

  The series of processes described above can be executed by hardware or can be executed by software. When a series of processing is executed by software, a program constituting the software is installed from a program recording medium into a computer incorporated in dedicated hardware or a general-purpose personal computer.

  FIG. 19 is a block diagram illustrating a hardware configuration example of a computer that executes the above-described series of processing by a program.

  A CPU (Central Processing Unit) 51, a ROM (Read Only Memory) 52, and a RAM (Random Access Memory) 53 are connected to each other by a bus 54.

  An input / output interface 55 is further connected to the bus 54. Connected to the input / output interface 55 are an input unit 56 such as a keyboard and a mouse, and an output unit 57 such as a display and a speaker. The bus 54 is connected to a storage unit 58 made up of a hard disk, a non-volatile memory, etc., a communication unit 59 made up of a network interface, etc., and a drive 60 that drives the removable media 61.

  In the computer configured as described above, for example, the CPU 51 loads the program stored in the storage unit 58 to the RAM 53 via the input / output interface 55 and the bus 54 and executes it, thereby executing the above-described series of processing. Is done.

  The program executed by the CPU 51 is recorded in, for example, the removable medium 61 or provided via a wired or wireless transmission medium such as a local area network, the Internet, or digital broadcasting, and is installed in the storage unit 58.

  The program executed by the computer may be a program that is processed in time series in the order described in this specification, or in parallel or at a necessary timing such as when a call is made. It may be a program for processing.

  The embodiments of the present invention are not limited to the above-described embodiments, and various modifications can be made without departing from the scope of the present invention.

  DESCRIPTION OF SYMBOLS 1 Recording / reproducing apparatus, 2 Network, 3 CM music information delivery server, 11 Broadcast receiving part, 12 Program recording part, 13 Feature-value extraction part, 14 Feature-value holding part, 15 CM section determination part, 16 Music section determination part, 17 Network transmission / reception unit, 18 CM song information holding unit, 19 CM song information / feature amount linking unit, 20 Music section / feature amount linking unit, 21 Match search unit, 22 Meta information holding unit, 23 Meta information presentation unit, 24 Playback section

Claims (6)

An acquisition means for acquiring CM song information, which is information including the name of the song used in the CM,
Extraction means for extracting the feature amount of the audio information of the recorded CM and the feature amount of the audio information included in the recorded content in the section where the music is played back,
When the section in which the song is played includes a section in which the feature amount of the voice information whose degree of coincidence with the feature amount of the recorded CM voice information is equal to or greater than a threshold value, the song is played back. An information processing apparatus comprising: setting means for setting information included in the CM music information as meta information of a section to be performed. The acquisition means communicates via a network with a server that associates and manages a CM provision time and the CM song information, and the CM song information that is managed in association with the recorded CM provision time The information processing apparatus according to claim 1. The information processing apparatus according to claim 1, further comprising: a display control unit that displays a name of a song included in the meta information set by the setting unit when presenting a section in which the song is played. The apparatus further includes a reproducing unit that reproduces a section in which a feature amount of audio information having a degree of coincidence with a feature amount of voice information of the recorded CM is extracted from a whole section in which the music is reproduced. Item 4. The information processing apparatus according to Item 1. Get CM song information that is the information including the name of the song used in the CM,
Extract the feature amount of the audio information of the recorded CM and the feature amount of the audio information of the section where the song is played, which is included in the recorded content,
If the section in which the song is played includes a section in which the feature amount of the voice information whose degree of coincidence with the feature amount of the voice information of the recorded CM is equal to or greater than a threshold value, the song is played back. An information processing method including a step of setting information included in the CM music information as meta information of a section to be played. Get CM song information that is the information including the name of the song used in the CM,
Extract the feature amount of the audio information of the recorded CM and the feature amount of the audio information included in the recorded content in the section where the song is played,
If the section in which the song is played includes a section in which the feature value of the voice information whose degree of coincidence with the feature value of the recorded CM voice information is equal to or greater than a threshold value, the song is played back. A program for causing a computer to execute a process including a step of setting information included in the CM music information as meta information of a section to be played.

Images