WO2001016935A1 - Procede et dispositif d'extraction/traitement d'informations, et procede et dispositif de stockage - Google Patents
Procede et dispositif d'extraction/traitement d'informations, et procede et dispositif de stockage Download PDFInfo
- Publication number
- WO2001016935A1 WO2001016935A1 PCT/JP2000/005771 JP0005771W WO0116935A1 WO 2001016935 A1 WO2001016935 A1 WO 2001016935A1 JP 0005771 W JP0005771 W JP 0005771W WO 0116935 A1 WO0116935 A1 WO 0116935A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- search
- signal
- acoustic
- searcher
- video
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 47
- 238000003672 processing method Methods 0.000 title claims description 23
- 238000012545 processing Methods 0.000 title description 62
- 238000004458 analytical method Methods 0.000 claims abstract description 56
- 230000005236 sound signal Effects 0.000 claims description 356
- 238000000605 extraction Methods 0.000 claims description 14
- 230000001419 dependent effect Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 5
- 230000032258 transport Effects 0.000 description 22
- 238000010586 diagram Methods 0.000 description 19
- 230000006835 compression Effects 0.000 description 13
- 238000007906 compression Methods 0.000 description 13
- 238000009826 distribution Methods 0.000 description 13
- 239000002131 composite material Substances 0.000 description 9
- 238000001514 detection method Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 239000003550 marker Substances 0.000 description 8
- 230000000694 effects Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 230000002194 synthesizing effect Effects 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 206010011878 Deafness Diseases 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/10—Indexing; Addressing; Timing or synchronising; Measuring tape travel
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H3/00—Instruments in which the tones are generated by electromechanical means
- G10H3/12—Instruments in which the tones are generated by electromechanical means using mechanical resonant generators, e.g. strings or percussive instruments, the tones of which are picked up by electromechanical transducers, the electrical signals being further manipulated or amplified and subsequently converted to sound by a loudspeaker or equivalent instrument
- G10H3/125—Extracting or recognising the pitch or fundamental frequency of the picked up signal
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/10—Indexing; Addressing; Timing or synchronising; Measuring tape travel
- G11B27/102—Programmed access in sequence to addressed parts of tracks of operating record carriers
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/10—Indexing; Addressing; Timing or synchronising; Measuring tape travel
- G11B27/102—Programmed access in sequence to addressed parts of tracks of operating record carriers
- G11B27/105—Programmed access in sequence to addressed parts of tracks of operating record carriers of operating discs
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/10—Indexing; Addressing; Timing or synchronising; Measuring tape travel
- G11B27/19—Indexing; Addressing; Timing or synchronising; Measuring tape travel by using information detectable on the record carrier
- G11B27/28—Indexing; Addressing; Timing or synchronising; Measuring tape travel by using information detectable on the record carrier by using information signals recorded by the same method as the main recording
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/10—Indexing; Addressing; Timing or synchronising; Measuring tape travel
- G11B27/34—Indicating arrangements
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H2240/00—Data organisation or data communication aspects, specifically adapted for electrophonic musical tools or instruments
- G10H2240/011—Files or data streams containing coded musical information, e.g. for transmission
- G10H2240/046—File format, i.e. specific or non-standard musical file format used in or adapted for electrophonic musical instruments, e.g. in wavetables
- G10H2240/066—MPEG audio-visual compression file formats, e.g. MPEG-4 for coding of audio-visual objects
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H2240/00—Data organisation or data communication aspects, specifically adapted for electrophonic musical tools or instruments
- G10H2240/171—Transmission of musical instrument data, control or status information; Transmission, remote access or control of music data for electrophonic musical instruments
- G10H2240/281—Protocol or standard connector for transmission of analog or digital data to or from an electrophonic musical instrument
- G10H2240/315—Firewire, i.e. transmission according to IEEE1394
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H2250/00—Aspects of algorithms or signal processing methods without intrinsic musical character, yet specifically adapted for or used in electrophonic musical processing
- G10H2250/541—Details of musical waveform synthesis, i.e. audio waveshape processing from individual wavetable samples, independently of their origin or of the sound they represent
- G10H2250/571—Waveform compression, adapted for music synthesisers, sound banks or wavetables
- G10H2250/575—Adaptive MDCT-based compression, e.g. using a hybrid subband-MDCT, as in ATRAC
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B2220/00—Record carriers by type
- G11B2220/20—Disc-shaped record carriers
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B2220/00—Record carriers by type
- G11B2220/20—Disc-shaped record carriers
- G11B2220/25—Disc-shaped record carriers characterised in that the disc is based on a specific recording technology
- G11B2220/2525—Magneto-optical [MO] discs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/79—Processing of colour television signals in connection with recording
- H04N9/80—Transformation of the television signal for recording, e.g. modulation, frequency changing; Inverse transformation for playback
- H04N9/804—Transformation of the television signal for recording, e.g. modulation, frequency changing; Inverse transformation for playback involving pulse code modulation of the colour picture signal components
- H04N9/8042—Transformation of the television signal for recording, e.g. modulation, frequency changing; Inverse transformation for playback involving pulse code modulation of the colour picture signal components involving data reduction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/79—Processing of colour television signals in connection with recording
- H04N9/80—Transformation of the television signal for recording, e.g. modulation, frequency changing; Inverse transformation for playback
- H04N9/804—Transformation of the television signal for recording, e.g. modulation, frequency changing; Inverse transformation for playback involving pulse code modulation of the colour picture signal components
- H04N9/806—Transformation of the television signal for recording, e.g. modulation, frequency changing; Inverse transformation for playback involving pulse code modulation of the colour picture signal components with processing of the sound signal
- H04N9/8063—Transformation of the television signal for recording, e.g. modulation, frequency changing; Inverse transformation for playback involving pulse code modulation of the colour picture signal components with processing of the sound signal using time division multiplex of the PCM audio and PCM video signals
Definitions
- the present invention relates to a search processing method and apparatus for searching, for example, a part of a specific musical instrument, a specific human voice, a sound of an animal, a specific person image, a specific scene, or the like from an audio signal or a video signal to be searched.
- the present invention also relates to an information storage method and apparatus using the search processing method and apparatus.
- the present invention does not require the operation of recording a marker or recording the count value and time at the time of recording, and also searches for a specific speaker or musical instrument. It is an object of the present invention to provide a method and an apparatus that can perform the method.
- the sound search processing method includes, for one or a plurality of sound signals as search elements, each of search element sound characteristic parameters consisting of sound characteristic parameters depending on structural elements of a sound source; By comparing the acoustic feature parameters obtained by analyzing the sound signal of the search target and the similarity between the two, and calculating the similarity between the two, the similarity to the sound signal of the search element is obtained from the sound signal of the search target. It is characterized by searching for a part.
- the input acoustic signal is recorded on a recording medium, and the input acoustic signal is analyzed to obtain an acoustic feature parameter dependent on a structural element of a sound source.
- a comparison is made between each of the search consonant characteristic parameters for one or more sound signals as one or more search signals and one or more of the acoustic characteristic parameters for the input sound signal.
- the acoustic information search device comprises: an acoustic feature parameter overnight analyzing means for analyzing an acoustic signal to be searched over an acoustic feature parameter dependent on a structural element of a sound source; A search is performed by comparing the acoustic characteristic parameter of the searcher composed of the acoustic characteristic parameters with respect to the signal and the acoustic characteristic parameter of the acoustic signal to be retrieved from the acoustic characteristic parameter analysis means.
- a search unit for searching a target audio signal for a portion similar to the audio signal from the sound source of the probe, and a result display unit for displaying a result of the search unit.
- the acoustic information search device comprises: an acoustic feature parameter overnight analyzing means for analyzing an acoustic signal to be searched over an acoustic feature parameter dependent on a structural element of a sound source; A comparison is made between a searcher acoustic feature parameter set consisting of the acoustic feature parameter set for the signal and an acoustic feature parameter set of the search target audio signal from the sound feature parameter set analysis unit, Searching means for searching for a part similar to the sound signal from the sound source of the searcher from the sound signal to be searched, and extracting and reproducing only the similar part based on a search result by the searching means And reproducing means for performing the operation.
- the acoustic information storage device includes a recording unit that records an input acoustic signal on a recording medium, and analyzes the input acoustic signal into acoustic characteristic parameters that depend on structural elements of a sound source.
- An acoustic feature parameter overnight analysis means each of the searcher acoustic feature parameters comprising one or more acoustic feature parameters for one or more audio signals to be a search element, and the above-mentioned input audio signal
- a search means for searching for a part similar to the acoustic signal from the sound source of the searcher from the acoustic signal to be searched is provided. And recording a search result of the search means in association with a position where the search element and the input audio signal are recorded on the recording medium.
- the audiovisual image search processing method is an audiovisual image search processing method for searching a predetermined portion from an input signal composed of a video signal and an audio signal related to the video signal.
- ⁇ Acoustic feature pattern of multiple sound signals depending on the structural elements of the sound source Comparing each of the acoustic feature parameters of the search element consisting of lame and the acoustic feature parameters obtained by analyzing the acoustic signal in the input signal to be searched, and calculating the similarity between the two. By doing so, a portion similar to the audio signal of the search element is searched for from the audio signal in the input signal, and the searched portion is used as a search result for the input signal.
- the audiovisual image search processing method is an audiovisual image search processing method for searching a predetermined portion from an input signal composed of a video signal and an audio signal related to the video signal. For each of a plurality of acoustic signals, each of the searcher acoustic feature parameters consisting of the acoustic feature parameters depending on the structural element of the sound source and the acoustic signal in the input signal to be searched are analyzed. By comparing the obtained acoustic feature parameters and the similarity, and calculating the similarity between the two, a portion similar to the acoustic signal of the searcher is retrieved from the acoustic signal in the input signal, and the retrieval is performed.
- each of the search child video feature parameters consisting of video feature parameters representing image features and the video signal in the input signal to be searched are solved.
- an image portion similar to the image of the search element is searched from the video signal in the input signal,
- a predetermined portion is searched from the input signal based on a search result for the signal and a search result for the video signal.
- the audiovisual information storage method records an input signal including a video signal and an audio signal related to the video signal on a recording medium, and analyzes the audio signal in the input signal.
- Sound source structure An acoustic feature parameter that depends on the structural element is obtained, and a search element comprising one or more of the acoustic feature parameters for one to a plurality of acoustic signals is used as a search element.
- a search element comprising one or more of the acoustic feature parameters for one to a plurality of acoustic signals is used as a search element.
- the audio-video information storage method records an input signal composed of a video signal and an audio signal related to the video signal on a recording medium, and includes a method for searching for one or more audio signals as a search element.
- Each of the searcher acoustic feature parameters consisting of the acoustic feature parameters depending on the structural elements of the sound source, the acoustic feature parameters obtained by analyzing the acoustic signal in the input signal to be searched, and By calculating the similarity between the two, a portion similar to the acoustic signal of the searcher is searched for from the audio signal in the input signal, and further a searcher is used.
- an image portion similar to the image of the search element is searched from the video signal in the input signal. Is recorded in association with the search element and the recording position of the input signal on the recording medium.
- the audiovisual information search device comprises: a video signal; An audio feature parameter analysis means for analyzing the audio signal in an input signal composed of an audio signal related to a video signal and an audio feature parameter dependent on a structural element of a sound source; For a signal, a searcher acoustic feature parameter set consisting of the acoustic feature parameter set and a sound feature parameter set of the search target audio signal from the acoustic feature parameter set analysis means are compared. It is characterized by comprising a search means for searching a part similar to the sound signal from the sound source of the search element from the sound signal to be searched, and a result display means for displaying a result of the search means.
- the audiovisual information search device may further include: converting the audio signal in an input signal including a video signal and an audio signal related to the video signal into an audio feature parameter dependent on a structural element of a sound source.
- An acoustic feature parameter overnight analyzing means for analyzing in the evening; a search element acoustic feature parameter overnight consisting of the acoustic feature parameter overnight for an acoustic signal as a search element; and A search unit for comparing a sound characteristic parameter of the search target audio signal with a search for a part similar to the sound signal from the sound source of the searcher from the search target audio signal; and the search unit.
- reproducing means for extracting and reproducing the input signal portion corresponding to the similar portion based on the search result at step (a).
- the audiovisual information retrieval apparatus may further include: converting the audio signal in an input signal including a video signal and an audio signal related to the video signal into an audio feature parameter dependent on a structural element of a sound source.
- An audio part searching means for searching for a part; a video characteristic parameter analyzing means for analyzing a video signal in the input signal over a video representing feature of an image; and one or more videos as search elements
- a comparison is made between each of the search child video feature parameters consisting of the video feature parameters for the signal and the video feature parameters of the video signal in the input signal from the video feature parameter analysis means.
- a video part search means for searching a video signal in the input signal for a part similar to the video signal of the search element; and a result display means for displaying results of the audio part search means and the video part search means. And a step.
- the audiovisual information search device may further include: converting the audio signal in an input signal including a video signal and an audio signal related to the video signal into an audio feature parameter dependent on a structural element of a sound source.
- Acoustic feature parameter overnight analysis means for analyzing in the evening; a search element acoustic feature parameter overnight comprising the acoustic feature parameter overnight for a sound source to be a search element; and the input from the acoustic feature parameter overnight analysis means
- a sound part search unit that compares a sound parameter of the sound signal in the signal with a sound parameter in the input signal and searches for a part similar to the sound signal from the sound source of the searcher from the sound signal in the input signal;
- a video feature parameter analyzing means for analyzing a video signal in the input signal into video feature parameters representing image features; and a video feature parameter analyzing means for one or more video signals as a search element.
- Video section search means for searching a video signal in the input signal for a portion similar to the video signal of the search element, and searching by the audio part search means and the video part search means Reproducing means for extracting and reproducing the input signal portion determined based on the result.
- the audio-video information storage device includes a recording unit that records an input signal composed of a video signal and an audio signal related to the video signal on a recording medium, and analyzes the audio signal in the input signal.
- Acoustic feature parameter analysis means for analyzing the acoustic feature parameters that depend on the structural elements of the sound source, and a search consisting of the above-described acoustic feature parameters for one or more sound signals as search elements By comparing each of the sub-acoustic feature parameters and the acoustic feature parameter of the audio signal in the input signal, and calculating the similarity between the two, the audio signal in the input signal has And a sound part search means for searching for a part similar to the sound signal of the search element from the search result.
- the search result of the sound part search means is stored in the storage position of the search element and the input signal on the recording medium. It is communicated, characterized in that to record it.
- the audiovisual information storage device includes: a recording unit that records an input signal including a video signal and an audio signal related to the video signal on a recording medium;
- a searcher composed of a set of acoustic feature parameters depending on the structural elements of a sound source for an acoustic signal. Each of the acoustic feature parameters and the acoustic signal in the input signal to be searched are obtained by analyzing the acoustic signal.
- an acoustic part search means for searching for a part similar to the acoustic signal of the searcher from the acoustic signal in the input signal, For each of one or more video signals as a search element, each of the search element video feature parameters consisting of video feature parameters representing image features and the video signal in the input signal to be searched are analyzed.
- a video portion search means for searching the video signal in the input signal for an image portion similar to the image of the searcher by comparing the video feature parameter and the obtained video feature parameter and calculating the similarity between the two. And recording the search results of the audio partial search unit and the video partial search unit in association with the search element and the recording position of the input signal on the recording medium.
- FIG. 1 is a block diagram of a first embodiment of a sound retrieval processing device according to the present invention.
- 2A and 2B are diagrams showing a frequency component distribution and a time waveform for showing acoustic features of a male voice.
- FIGS. 3A and 3B are diagrams showing a frequency component distribution and a time waveform for showing acoustic features of a female voice.
- FIG. 4A and FIG. 4B are diagrams showing frequency component distributions and time waveforms for showing acoustic characteristics of saxophones.
- 5A and 5B are diagrams showing a frequency component distribution and a time waveform for showing the acoustic characteristics of the base band.
- FIG. 6 is a flowchart for explaining a search element registration processing operation in the first embodiment.
- FIG. 7 is a flowchart illustrating a search processing operation according to the first embodiment.
- FIGS. 8A and 8B are diagrams showing display examples of search processing results according to the first embodiment.
- FIG. 9 is a diagram illustrating another example of the display example of the search processing result according to the first embodiment.
- FIG. 10 is a diagram illustrating another example of the display example of the search processing result according to the first embodiment.
- FIG. 11 is a block diagram of a second embodiment of the sound retrieval processing device according to the present invention.
- FIG. 12 is a block diagram of a third embodiment of the sound retrieval processing device according to the present invention.
- FIG. 13 is a block diagram of a fourth embodiment of the sound retrieval processing device according to the present invention.
- FIG. 14 is a diagram used to explain a main part of a fifth embodiment of the sound retrieval processing device according to the present invention.
- FIG. 15 is a flowchart used to explain the main part of a fifth embodiment of the sound retrieval processing device according to the present invention.
- FIG. 16 is a block diagram of the first embodiment of the audiovisual image search processing device according to the present invention.
- FIG. 17 is a diagram used for explaining the first embodiment of the audiovisual image search processing device according to the present invention.
- FIG. 1 is a block diagram of a first embodiment of the present invention.
- the first embodiment has a function of recording and reproducing an input audio signal to be searched, for example, an input audio signal picked up by a microphone.
- the reproduced audio signal also has a function of being an audio signal to be searched.
- the input audio signal is supplied to the switch circuit SW 1 through the input terminal 11.
- the switch circuit SW1 is switched to the terminal a when recording the input audio signal and when searching for the input audio signal by the switching signal from the control unit 10, and switches the audio signal of the search element from the input audio signal. When extracting, it is switched to the terminal b side.
- the audio signal obtained on the terminal a side of the switch circuit SW 1 is transmitted to a recording medium 13, for example, a memory card, an optical disk such as a magnetic disk or a magneto-optical disk, or a hard disk via an acoustic signal recording unit 12. Recorded on the disc.
- the sound signal recording unit 12 is activated by a control signal from the control unit 10 and performs recording when a recording instruction is given from the user through the key operation unit 20. .
- the input audio signal through the input terminal 11 is also supplied to the input terminal IN of the switch circuit SW2.
- An audio amplifier 15 and a speaker 16 are connected to the subsequent stage of the switch circuit SW2, and the switch circuit SW2 receives an input terminal according to a switching control signal from the control unit 10 except during reproduction described later. Switch to IN side. Therefore, at times other than reproduction, the input audio signal is supplied to the speaker 16 through the audio amplifier 15 and is reproduced as sound.
- the control signal from the control unit 10 activates the sound signal reproduction unit 14 and reads the reproduction sound signal from the recording medium 13. Then, it is reproduced and supplied to the input terminal PB of the switch circuit SW2.
- the switch circuit SW2 is switched to the input terminal PB side by a switching control signal from the control unit 10. Therefore, the reproduced sound signal is supplied to the speaker 16 through the audio amplifier 15 and reproduced.
- the input audio signal obtained on the terminal a side of the switch circuit SW1 is also supplied to one input terminal d of the switch circuit SW3.
- a reproduced sound signal from the sound signal reproducing unit 14 is supplied to the other input terminal c of the switch circuit SW3.
- the switch circuit SW3 switches the audio signal to be searched, and is switched according to a user's instruction to select the audio signal to be searched through the key operation unit 20.
- the acoustic signal to be searched for obtained from the switch circuit SW 3 is supplied to the acoustic feature parameter analysis unit 21, and for example, structural elements of the sound source such as the difference in the structure of the sounding body and the resonance system.
- Dependent acoustic features Analyze the parameters overnight.
- Such acoustic feature parameters include pitch frequency, its harmonic component frequency, formant frequency, cepstrum information, linear prediction coefficient and its residual signal, Percoll coefficient, and the like.
- Fig. 2 shows the frequency component distribution of a typical male voice
- FIG. 3 shows the frequency component distribution (Fig. 3 (A)) and time waveform (Fig.
- FIG. 4 shows an example of the saxophone frequency component distribution (Fig. 4 (A)) and the time waveform (Fig. 4 (B)).
- Figure 1 shows an example of the saxophone frequency component distribution (Fig. 4 (A)) and the time waveform (Fig. 4 (B)).
- Figure 2 shows an example of the saxophone frequency component distribution (Fig. 4 (A)) and the time waveform (Fig. 4 (B)).
- Figs. 2 to 5 are simply frequency component distributions and time waveforms, and it can be seen that acoustic characteristics are found in the pitch frequency, its harmonic components, the formant structure, and its presence or absence.
- the characteristics of an acoustic signal can be represented by acoustic feature parameters such as a linear prediction coefficient and its residual signal.
- the inflection parameter of speech obtained from the temporal variation of the pitch frequency is also effective as a parameter parameter representing the characteristics of the sound signal. Can be distinguished from the situation. For example, if the pitch is lower than usual and the inflection tends to decrease, it is identified as a situation that is not energetic-a situation that is sad. Therefore, the intonation information can also be used for the acoustic feature parameters.
- the acoustic feature parameters from the acoustic feature parameter analyzer 21 are: It is supplied to the similarity calculation unit 22.
- the similarity calculation unit 22 includes an audio feature parameter set (hereinafter referred to as a search element acoustic feature set) for an audio signal serving as a search element, and an acoustic feature parameter set analysis unit 21. Calculate the similarity of the audio signal to be searched with the acoustic feature parameters.
- the similarity calculation in the output unit 22 is not based on the similarity determination of the sound time-series waveform pattern such as voice recognition, but is generated from a sound source having a similar structure for the sounding body and the resonance system. It is a judgment. Since it does not calculate the coincidence or similarity of the time-series waveform patterns, for example, when reproducing an audio signal, the similarity can be calculated even if the reproduction speed is increased.
- the search feature acoustic feature parameters in a section of a certain time width TW are (x0, y0, z0), and the acoustic feature parameters of the search target acoustic signal are (X i, yi, zi), the similarity calculator 22 calculates the distance S between the two as the similarity as shown in the following equation.
- the above-mentioned time width TW is set in advance by the similarity calculation unit 22 in consideration of parameter information and time sufficient for determining similarity.
- sqrt () indicates the square root operation in (). The smaller this distance S is, the greater the similarity is. You.
- the similarity calculation unit 22 calculates the distance S for each section of a predetermined time width TW, and when the calculated distance S is smaller than a predetermined value Sth.
- the sound signal in the section of the time width TW is determined to be the same or similar to the sound signal of the search element, and otherwise, it is determined to be dissimilar.
- the similarity determination output of the similarity calculation unit 22 is supplied to the display unit 24 via the display control unit 23.
- the display control unit 23 outputs the similarity determination output in correspondence with the time from the beginning of the audio signal to be searched, for example, as in a horizontal bar graph, on the screen of the display unit 24. (See Fig. 8 etc. which will be described later).
- an audio signal as a search element is extracted from an input audio signal or a reproduced audio signal and stored in the storage unit 32 in advance.
- the input audio signal obtained at the terminal b of the switch circuit SW1 is supplied to the input terminal f of the switch circuit SW4, and the reproduced audio signal from the audio signal reproduction unit 14 is supplied to the switch circuit SW4. It is supplied to input terminal e.
- the switch circuit SW 4 switches whether to extract the sound signal of the search element from the input sound signal or to extract the sound signal from the reproduced sound signal.
- the key operation unit is controlled by a control signal from the control unit 10. Switching is performed according to a user's selection instruction through 20.
- the sound signal from the switch circuit SW 4 is used to extract the searcher sound signal. It is supplied to the storage unit 31.
- a control signal corresponding to the operation of the user through the key operation unit 20 is supplied from the control unit 10 to the search child acoustic signal extraction storage unit 31.
- the user operates the key operation unit 20 while listening to the input audio signal from the loudspeaker or the sound reproduction output sound of the reproduction sound signal, when the sound signal part to be used as a search element is obtained.
- Operate the searcher instruction key (not shown).
- an audio signal in a section of a predetermined time width TW including the key operation time point is extracted and stored in the search memory 32.
- the search element memory 32 has a storage area for each search element, and each search element is stored in a separate storage area.
- the searcher acoustic signal extraction storage unit 31 is provided with a buffer memory so that the section of the time width TW starts from a point slightly before the key operation point.
- the sound signal in the section of the designated time width T W is stored in the searcher memory 32 as a searcher sound signal.
- a plurality of search elements can be stored, and each time the user specifies a sound signal of the search element, a search signal in the search element memory 32 is obtained by a control signal from the control section 10.
- the storage area is updated. That is, the search element storage area address is updated.
- the acoustic signal of the search element in the section of the time width TW extracted by the user's instruction from the search element acoustic signal extraction storage unit 31 is searched according to the switching control signal from the control unit 10.
- the switch circuit SW5 is switched in synchronization with the update of the search element storage area of the child memory 32, the data is sequentially stored in separate search element storage areas of the search element memory 32.
- the acoustic signal of A memo can be entered via the key operation unit 20 to indicate whether the data has been stored in the memory 32.
- the memo entry of the search element is displayed in a table format, for example, corresponding to the search element storage area number. It is shown in part 24.
- the user can execute a search with a desired search element by referring to the search element table on the display unit 24 and specifying the search element storage number in which the search element to be searched is stored. That is, when the user selects a search mode through the key operation unit 20 and designates a predetermined search element storage area number, the switch circuit SW 6 is switched by the control signal from the control unit 10 and the search is performed.
- the child acoustic signal reading unit 33 reads the acoustic signal of the search element from the specified search element storage area of the search element memory 32.
- the read-out acoustic signal of the searcher is supplied to the searcher acoustic feature parameter analyzer 34 and analyzed, whereby the searcher acoustic feature parameter of the searcher acoustic signal is obtained.
- the searcher acoustic feature parameters are supplied to the similarity calculator 22 described above, and as described above, for each section of the time width TW, the searcher performs Is searched for.
- FIG. 6 is a flowchart of an operation mainly performed by the control unit 10 when the search element is registered. The processing routine shown in FIG. It starts when the search child registration mode is selected through 0.
- the search child registration operation will be described with reference to FIG.
- control unit 10 determines a user's selection instruction through the key operation unit 20, and determines whether to extract a search element from an input audio signal or a search element from a reproduced audio signal (step S10).
- the control unit 10 switches the switch circuit SW1 to the output terminal b, the switch circuit SW2 to the input terminal IN, and the switch circuit SW4. Switches to the input terminal f side (step S102).
- the control unit 10 switches the switch circuit SW1 to the output terminal a, the switch circuit SW2 to the input terminal PB, and the switch circuit SW4 to the input terminal e. (Step S103).
- step S104 the control unit 10 waits for an instruction of the acoustic signal portion of the search element by the user through the key operation unit 20.
- the audio signal from which the search element is extracted is supplied to the sub-power 16 through the audio amplifier 15 and is reproduced as sound.
- the user listens to the sound emitted from the speaker 16 and instructs, through the key operation unit 20, an acoustic signal part desired to be used as a searcher, for example, a specific searcher sound source such as a specific speaker.
- step S104 when the instruction input of the acoustic part of the search element is detected, the control unit 10 updates the search element storage area of the search element memory 32 (step S105), and extracts the search element acoustic signal.
- the storage unit 31 is controlled so as to extract the sound signal in the section of the fixed time width TW as described above (step S106).
- control is performed so that the extracted acoustic signal portion of the search element is written into the updated search element storage area of the search element memory 32 (step S 107).
- step S108 it is determined whether or not an instruction to end the search element registration mode has been issued through the key operation unit 20 (step S108). If the end instruction has been issued, the search element registration mode processing routine is executed. If there is no end instruction, the process returns to step S104, and waits for the user to input the next search element extraction instruction, and repeats the above operation.
- the searcher memory 32 can register and store the searcher's sound signal extracted from the input sound signal or the reproduced sound signal by the user. In this case, if the memory capacity of the search element memory 32 is sufficient, the sound signal of the search element can be stored without being erased.
- the similarity is calculated by using the acoustic feature parameters. Therefore, the accumulated acoustic signal of the searcher is similar to the audio signal portion of the searcher from the extracted audio signal. It is used not only when searching for a part to be searched, but also when searching for a part similar to the sound signal part of the searcher for another search target audio signal that is not an extracted one. Can be.
- the search processing is executed as follows using the acoustic signal of the search element stored in the search element memory 32.
- Figure 7 shows the processing routine for this search processing.
- the processing routine of FIG. 7 is started when the user selects the search processing mode through the key operation unit 20.
- the control unit 10 determines a user's selection instruction through the key operation unit 20 and determines whether a search target is an input audio signal or a reproduced audio signal (step S201).
- the control unit 10 switches the switch circuit SW 1 to the output terminal a, the switch circuit SW 2 to the input terminal IN, and the switch circuit SW 2 to the input terminal IN.
- SW3 switches to the input terminal d side (step S202).
- the control unit 10 switches the switch circuit SW2 to the input PB side and switches the switch circuit SW3 to the input terminal c side (step S20). 3) o
- step S204 the control unit 10 recognizes what the user has selected as a search element (step S204). ), And control so that the acoustic signal of the selected probe is read out from the retriever memory 32 (step S205).
- the acoustic signal of the search element read from the memory 32 is supplied to the search element acoustic feature parameter analysis section 34 via the search element acoustic signal reading section 33, and the search element acoustic feature parameter is read. Evening, similarity calculation Supplied to part 22.
- the similarity calculator 22 performs the above-described similarity calculation between the acoustic feature parameters of the audio signal to be searched, for example, for each section of the time width TW, and the probe acoustic feature parameters.
- the similarity which is an index of the similarity between the two, is calculated (step S206). In this example, as described above, the similarity is obtained as the distance S between the two.
- step S207 it is determined whether or not the distance S, which is the similarity, is smaller than a predetermined threshold Sth. If the distance S is smaller than the threshold Sth, the sound similar to the search element is determined. It is determined as a signal portion (step S208), and when it is larger than the threshold value Sth, it is determined that they are dissimilar (step S209). Then, the determination result is displayed on the screen of the display unit 24 via the display control unit 23 (step S 21
- step S211 upon completion of the audio signal to be searched or by a user's termination instruction, it is determined whether or not the search processing has been completed (step S211). End the routine, otherwise return to step S206 and continue searching with the search term.
- Figure 8 shows a display example of the search results as described above.
- the example in FIG. 8 is a case where the search target is a reproduced audio signal of a conference recording and the search element is a specific speaker A. According to this display example, at which time position in the entire conference recording speaker A is speaking is shown.
- search element has been described. However, a plurality of search elements are specified, and the similarity of the plurality of search elements is calculated. Can also be displayed. In this case, for example, the search element may be switched in a time-division manner every 10 milliseconds, and the similarity calculation unit 22 may perform the calculation operation.
- a plurality of similarity calculation units may be provided, and the similarity calculation units may calculate the similarity for each of the plurality of search elements in parallel.
- Fig. 9 shows a display example of search results obtained by performing a search by setting a plurality of search elements in this way.
- This display example shows the time intervals of three speakers A, B, and C in the entire conference recording.
- the similarity determination result is a binary result based on whether or not a predetermined threshold has been exceeded.
- the distance S as the similarity calculation result is calculated.
- the value may be directly reflected on the display. That is, the shorter the distance S is, the higher the similarity is, and according to the high similarity, the time section display is displayed with shading as shown in Fig. 8 (B). You may. For example, in the example of FIG. 8 (B), the higher the shade, the higher the similarity. Also, instead of shading, differences in the degree of similarity may be displayed by differences in display colors.
- the display color of the similarity judgment output is made different for each search element. Alternatively, it may be displayed.
- the similarity determination output is displayed corresponding to the passage of time of the audio signal to be searched.
- the audio signal to be searched is a reproduced audio signal
- the recording medium 1 of the audio signal in each time interval is used.
- the recording position on 3 can be easily known. Therefore, once the similarity judgment display output as the search result for the reproduced sound signal is obtained, while displaying it on the display unit 23, the similarity judgment display output is displayed as shown in FIG.
- the playback position can be displayed in correspondence with, for example, a prosodic position.
- the search target audio signal can be played back from the position of the specified playback position force. it can.
- the search makes it possible to extract and reproduce the audio signal for each of the classified search elements from the audio signal to be searched.
- the sound characteristic parameter is used. Therefore, a sound using a pattern matching process for determining whether or not the waveform patterns match is used. Unlike voice recognition, there is no need to use the time-series waveform of the acoustic signal as it is. For this reason, when the playback audio signal is to be searched, the same similarity judgment output can be obtained even if the playback speed is not normal speed (1x speed) but high-speed playback such as 2x speed or 3x speed. it can. Therefore, it is possible to increase the search speed.
- the address on the recording medium can be associated with the search result, and only the audio signal portion similar to the specific search element is extracted from the recording medium using the search result. It is also possible to make it play back.
- the search target is a reproduced sound signal.
- the input sound signal is searched for using the input sound signal as a search target using a search element registered in advance.
- search element registered in advance.
- the sound signals of a plurality of musical instruments are registered as search elements, and the type of instrument used to play each part of the input sound signal can be classified and displayed.
- the search elements are extracted from the input sound signal and the reproduced sound signal and stored in the search element memory 32.
- the search element library includes a plurality of search elements. Search signal memory
- the similarity was calculated as the geometric distance S between the acoustic feature parameters, but a new parameter was calculated from several parameters, and the acoustic feature parameters were calculated using the new parameters. You can ask for the evening distance.
- the acoustic feature parameters of the search target and the search element are obtained.
- the evening distance may be calculated. It is also possible to calculate the similarity focusing on important parameters by weighting the parameters of each acoustic feature.
- the searcher memory 32 may be a memory card or the like that can be taken out instead of a built-in memory.
- a plurality of types of search elements are stored and prepared in a plurality of memory cards, and a memory card is exchanged according to an audio signal to be searched, thereby obtaining a desired search object. For, the search using the desired search element can be easily performed.
- a sound source of an acoustic signal to be used as a search element is prepared, and an acoustic signal from the sound source is input from an input terminal 11 in advance, and stored as a search element acoustic signal in a search element memory 32. You can also. Furthermore, instead of storing in the searcher memory 32, the sound signal from the sound source of the searcher is input separately from the sound signal to be searched, and the sound signal of the searcher is temporarily stored in the sofa memory. May be used for search. It should be noted that the search element is not limited to an audio signal from a single sound source, but may be an audio signal in a predetermined section extracted from an input audio signal or a reproduced audio signal.
- the image can also be displayed on the display unit.
- the classification of the search results can be confirmed. For example, you can search and classify recordings using audio signals.
- FIG. 11 shows a processor of the audio signal search processing device according to the second embodiment.
- the block diagram is shown.
- the acoustic signal is stored as a registered search element.
- the acoustic feature parameters are stored in the search element memory 32 as the registered search element. Store it.
- Other configurations are exactly the same as those of the apparatus of FIG. 1, and the same parts as those of FIG. 1 are denoted by the same reference numerals.
- a search element acoustic signal extraction unit 35 is provided on the output side of the switch circuit SW4. This corresponds to a part of the means for extracting the acoustic signal portion of the search element specified by the user in the search element acoustic signal extraction storage unit 31 in FIG.
- the acoustic signal of the search element extracted by the search element acoustic signal extraction unit 35 is analyzed by the search element acoustic feature parameter analysis unit 36, and is set as an acoustic feature parameter. It is stored in the search memory 32 through the overnight storage section 37 and the switch circuit SW5.
- the search element acoustic feature parameter storage unit 37 stores the search information in the search element acoustic signal extraction storage unit 31 in FIG. In the same manner as described above, each of the search elements (in this embodiment, the acoustic feature parameters) is stored separately in the search element memory 32. Write to the search area.
- the acoustic feature parameters of the search element stored in the search element memory 32 are changed by the control signal from the control section 10 generated based on the user's instruction through the key operation section 20. 6 and search are read by the child acoustic feature parameter reading unit 38.
- the read-out data is the audio feature parameters, the read-out data is directly supplied to the similarity calculation unit 22 and searched. A similarity calculation is performed.
- the second embodiment is different from the first embodiment only in that the searcher acoustic feature parameters are stored in the searcher memory 32.
- the searcher registration operation and the search operation using the searcher are performed in the following manner. This is performed in the same manner as in the first embodiment. Therefore, according to the second embodiment, the same functions and effects as those of the above-described first embodiment can be obtained. Further, modifications similar to those of the above-described first embodiment are possible.
- the searcher stores not the sound signal itself but the searcher acoustic feature parameters in the searcher memory 32, so that the storage capacity per searcher is smaller. It is possible to reduce the number, and to increase the number of search elements that can be stored and accumulated.
- the third embodiment is a case in which an acoustic feature parameter that can be re-synthesized into an acoustic signal is used. Since it is possible to re-synthesize the acoustic feature parameter into the acoustic signal, the recording of the acoustic signal is also recorded as the acoustic feature parameter. Then, in the third embodiment, as in the second embodiment, the searcher stores the sound characteristic parameters in the searcher memory 32.
- FIG. 12 is a block diagram of the acoustic signal search processing device according to the third embodiment. Also in FIG. 12, the same parts as those in the above-described embodiment are denoted by the same reference numerals.
- a parameter of a vocoder is used as the parameter of the acoustic feature.
- an input audio signal is supplied to an audio characteristic parameter analysis unit 41 through an input terminal 11, for example, a vocoder-type audio.
- the feature parameters are analyzed overnight.
- the acoustic feature parameter overnight from the acoustic feature parameter overnight analyzing unit 41 is supplied to the acoustic feature parameter overnight recording unit 42 through the switch circuit SW 1, and under the control of the control unit 10,
- the acoustic feature parameter recording unit 42 records the acoustic feature parameter of the input acoustic signal on the recording medium 13.
- the acoustic feature parameters of the input acoustic signal recorded on the recording medium 13 are reproduced by the acoustic feature parameter reproducing unit 43 under the control of the control unit 10, and are transmitted to the acoustic signal synthesizing unit 44. Supplied.
- the acoustic signal synthesizing unit 44 synthesizes the original audio signal from the acoustic feature parameters.
- the reproduced sound signal obtained from the sound signal synthesizing section 44 is supplied to the speaker 16 through the audio amplifier 15 through the input terminal PB of the switch circuit SW2, and is reproduced as sound.
- the input audio signal from the input terminal 11 is supplied to the speaker 16 through the input end IN of the switch circuit SW2 and the audio amplifier 15 and is reproduced as sound in the first and second embodiments. This is the same as the case of the embodiment.
- the acoustic feature parameter analysis unit 21 is not provided, and the switch circuit SW 3 is connected to the output terminal a of the switch circuit SW 1 to output the acoustic feature parameter of the input audio signal.
- One of the sound characteristic parameter and the reproduced sound characteristic parameter from the sound characteristic parameter reproducing unit 43 is determined by the switching control signal from the control unit 10 according to the user's instruction through the key operation unit 20. Select to the similarity calculator 2 2 Supply.
- the searcher stores the searcher acoustic feature parameters in the searcher memory 32 in the third embodiment, as in the second embodiment.
- the acoustic feature parameter the acoustic feature parameter from the evening analysis unit 41 is transmitted to one of the switch circuits SW 4 through the output terminal b of the switch circuit SW 1.
- the input audio signal f is supplied to the input terminal f, and the reproduced audio parameter from the audio characteristic parameter overnight reproducing unit 43 is supplied to the other input terminal e of the switch circuit SW4.
- the switch circuit SW 4 receives the switching control signal from the control unit 10 and determines whether or not to extract the acoustic feature parameters of the search element from the input audio signal or from the reproduced audio signal.
- the terminal is switched to either terminal e or input terminal.
- the acoustic feature parameters from the switch circuit SW 4 are supplied to the searcher acoustic feature parameter overnight storage unit 45.
- the user listens to the input audio signal from the speaker or the audio reproduction output of the reproduced audio signal, Operate the searcher instruction key (not shown) of the key operation unit 20.
- the retrieval child acoustic feature parameter extraction storage unit 45 extracts the acoustic characteristic parameters of the acoustic signal in the section of the predetermined time width TW including the key operation time point, and stores them in the retrieval child memory 32. Store in search element storage.
- the searcher memory 32 stores the sound characteristic parameters of the searcher's sound signal extracted from the input sound signal or the reproduced sound signal.
- the searcher acoustic feature parameters stored in the searcher memory 32 are stored in the searcher memory 32 in the same manner as in the above-described second embodiment.
- it is read out by the searcher acoustic feature parameter overnight reading unit 38 and supplied to the similarity calculating unit 22.
- the recording capacity of the recording medium can be effectively utilized.
- the acoustic feature parameter overnight analysis unit can be used as a common one for the search target and the search element, and the configuration is simplified. Can be changed.
- resynthesizable acoustic feature parameters include MPEG (Moving Picture Experts Group) sound compression formats (MPEG audio layer I, layer II, layer III). ) Data transfer and ATRAC (Adaptive Transform Acoustic Coding) ⁇ type data transfer.
- MPEG Motion Picture Experts Group
- ATRAC Adaptive Transform Acoustic Coding
- subband coding is performed by subdividing the audio band into multiple parts in order to use human auditory psychological characteristics efficiently.
- MP EG audio In layer I the entire band of the audio signal is divided into 32 subbands with equal frequency widths, and each signal is subsampled and encoded at 1/32 of the original sampling frequency.
- the band level distribution of the band Calculation, calculation of the main band frequency, detection of the harmonic structure, detection of the time transition of the main band frequency, etc. are performed, and the detection results are used as the searcher acoustic feature parameters.
- the audio feature parameter analysis unit 41 When applying the method of using the audio compression format data and ATRAC format data of the MPEG audio standard to the example in Fig. 12, when the input audio signal from the input terminal 11 is an analog signal or linear PCM signal, In this case, the audio feature parameter analysis unit 41 generates the audio compression format data of the MPEG standard or ATRAC format data. Then, the recording unit 42 records the acoustic compression data on the recording medium 13.
- the subband data is generated from the acoustic compression data from the acoustic feature parameter analysis unit 41 or the audio compression data from the reproduction unit 43, As described above, for the data of the subband, calculation of the band level distribution, calculation of the main band frequency, detection of the harmonic structure, detection of the time transition of the main band frequency, etc. are performed, and the detection results are searched. It is written in the searcher memory 32 as a parameter of the child acoustic feature.
- an acoustic feature parameter analysis unit is provided in the preceding stage of the similarity calculation unit 22 as in the examples of FIGS. 1 and 11, and the acoustic compression from the switch SW1 or the reproduction unit 43 is performed.
- Subband from data As described above, for the sub-band data, the band level distribution, the main band frequency is calculated, the harmonic structure is detected, and the time transition of the main band frequency is detected. To do. In this case, the configuration of the acoustic feature parameter overnight analysis unit is simplified. Then, the similarity calculation unit 22 compares the acoustic feature parameters obtained through the analysis with the searcher acoustic feature parameters from the searcher acoustic feature parameter readout unit 38 and performs similarity determination. .
- the input audio signal from the input terminal 11 is an analog signal or a linear PCM signal, but I EEE (The Ins tit ut eof Electrical and Electronic Enginers, Inc.) If the signal is input as a serial digital signal from a 1394 standard interface, or if a signal obtained as a digital audio compression signal is input to a digital broadcast receiver, the MPEG standard audio Since the compression format data and the ATRAC format data can be obtained as they are, the acoustic feature parameter analyzer 41 in FIG. 12 is not required.
- the above-described search method using the acoustic compression signal as a search target has a longer time lag for analysis than decoding the digital audio compression format data and converting it back to a linear PCM audio signal and then performing acoustic feature analysis.
- the sound characteristic parameter is recorded on the recording medium instead of the sound signal.
- the sound signal and the sound characteristic parameter are mutually recorded. It is recorded on a recording medium incidentally.
- the acoustic signal is an acoustic signal. Since the recording is performed together with the feature parameters, the acoustic feature parameters are not limited to those that can be re-synthesized into an acoustic signal as in the third embodiment.
- the sound characteristic parameter is recorded on a recording medium such as a magnetic disk, a magneto-optical disk, an optical disk, and a memory card along with the sound signal.
- the sound signal and the sound characteristic parameter are recorded on the recording medium for each sound signal recording unit section (a section such as a pack, a packet, and a sector).
- the data and the acoustic feature parameters for the corresponding unit section are recorded in a form that can be mutually associated, such as adjacent recording areas, that is, in a linked structure.
- FIG. 13 is a block diagram of the acoustic signal search processing device according to the fourth embodiment.
- the same parts as those shown in FIGS. 1, 11, and 12 of the above-described embodiment are denoted by the same reference numerals, and detailed description thereof will be omitted.
- the input audio signal through the audio input terminal 11 is supplied to the audio signal recording unit 12 through the switch circuit SW7.
- the switch circuit SW 7 is turned on during recording by a switching control signal from the control unit 10. Then, in the fourth embodiment, the input audio signal through the audio signal recording unit 12 is supplied to the recording data control unit 51.
- the input audio signal through the input terminal 11 is supplied to the acoustic feature parameter analyzing unit 41, and is analyzed in the acoustic feature parameter.
- the acoustic feature parameter from the acoustic feature parameter analyzer 41 is used as a switch circuit S as an acoustic feature parameter of the input audio signal to be searched.
- the sound feature parameter data from the sound feature parameter data analysis unit 41 is supplied to the recording data control unit 51.
- the recording / night control unit 51 records the sound signal and the sound characteristic parameter in a predetermined recording format in association with the recording.
- the recording controller 51 records the sound signal on the recording medium 13 for each recording unit section, as described above, and records the sound signal for the corresponding recording unit section.
- the characteristic parameters are recorded on the recording medium 13 at a position adjacent to the acoustic signal recording position.
- the input sound signal and its sound characteristic parameters recorded on the recording medium 13 in the recording format as described above are reproduced by the read data control unit 52 under the control of the control unit 10. That c Then, the acoustic signal reproduced from the recording medium 1 3 at the read data control unit 5 2 is supplied to the audio signal reproducing unit 1 4, through the input end PB side of the switch circuit SW 2, a speaker through an audio amplifier 1 5 The sound is supplied to 16 and is reproduced.
- the corresponding acoustic feature parameter reproduced from the recording medium 13 by the read-out data controller 52 is the input of the switch circuit SW 3 as the acoustic feature parameter of the reproduced audio signal to be searched. In addition to being supplied to c, it is also supplied to an input terminal e of a switch circuit SW4 in order to extract an acoustic feature parameter of the searcher from the reproduced audio signal.
- the audio signal and the audio feature parameter reproduced from the recording medium 13 by the read-out data controller 52 are added to the audio signal by another device.
- it can be transferred to the outside through the external output terminal (not shown). Therefore, it is not necessary to provide an acoustic feature parameter analysis unit in order to create an acoustic feature parameter in another apparatus for performing a search.
- the input sound signal and its sound characteristic parameters are recorded on a recording medium by the recording data control unit 51 in a linked state, and are linked to each other.
- the point that the read data control unit 52 reads and reproduces the acoustic signal and the acoustic feature parameter is different from the above-described embodiment, but the search is performed using the acoustic feature parameter.
- the third embodiment is similar to the third embodiment in that the searcher acoustic feature parameters can be extracted from the input audio signal and the reproduced audio signal.
- the search object and the search element can be made one common, and the configuration can be simplified. Also, when performing a search using another search device, the sound feature parameter analysis unit can be provided to the other search device. Therefore, another search device is provided with an acoustic feature parameter analysis unit. There is an advantage that there is no need.
- the audio signal to be recorded and the corresponding acoustic feature parameter need only be recorded on the recording medium in a linked manner, and therefore need not be recorded adjacently as in the above-described example.
- Acoustic in advance to the medium The recording area of the signal and the recording area of the sound feature parameter are determined separately, and the corresponding sound signal and the sound characteristic parameter are recorded in the (linked) address corresponding to each recording area. It may be recorded. Alternatively, the link information of the sound signal and the sound feature parameter—evening may be separately recorded, and the link information may be used to associate and reproduce the link information.
- the search target audio signal can be searched for by performing similarity determination with the searcher based on the acoustic feature parameters. While recording, the search for the specified search element can be performed in parallel. Therefore, at the end of recording, a search result for the search element for the audio signal to be searched is obtained. Therefore, it is also possible to record this search result on a recording medium that is separate from the acoustic signal recording area.
- the search result of the reproduced audio signal can be recorded later on the recording medium by preparing an area separate from the recording area of the audio signal on the recording medium.
- the search result is recorded together with the audio signal to be searched.
- a search for an input audio signal to be recorded is performed in parallel with the recording process using one or a plurality of search elements registered in advance.
- a disk medium such as a magnetic disk, a magneto-optical disk, or an optical disk or a memory card is used. In that case, At the time of recording, recording is performed while monitoring the address on the recording medium.
- an address (recording position) on a recording medium on which an audio signal portion determined to be similar is recorded is identified by the search element.
- switching control information of the switch circuit SW 6 (corresponding to a search element storage area, that is, a search element number) is used as the search element identification information.
- FIG. 14 shows a search result as a table after the end of recording in the case of the fifth embodiment.
- This table serves as a search index table for signals recorded on the recording medium.
- the searcher name is, for example, a name given in advance when the searcher was registered.
- the section data is data indicating a section determined to be similar to the search element, and is represented by a start address ST and an end address ED of the section.
- ADR i (i is an integer) indicates an address value on the recording medium.
- the information of the search index table is recorded in a predetermined recording area on a recording medium separately from the recording audio signal.
- FIG. 15 shows a processing routine for the search and reproduction.
- a search / playback instruction was issued through the key operation unit. Sometimes it starts.
- the search index data for creating the search index table is read from the recording medium (step S301).
- the control unit 10 creates a search index table as shown in FIG. 14 based on the read data and displays it on the display screen (step S302).
- the user looks at the displayed search index table, and inputs a search element to be searched and reproduced through the key operation unit. Then, the search element specified by the user is recognized (step S303). Then, with reference to the search index table, the section data determined as a similar section is recognized for the recognized search element (step S304). Then, the sound signal of the address section indicated by the recognized section data is sequentially read out from the recording medium and reproduced (step S305).
- the fifth embodiment it is possible to easily extract and reproduce only the sound signal portion similar to the search element.
- it is of course it is of course possible to perform a search by specifying a search element that is not in the search index table from the search element memory.
- the identification information of the search element and the search element name are included in the search index table.
- the sound signal of the search element is replaced with the search element name, or It may be recorded at the same time. By doing so, it is possible to easily find out what kind of sound signal the search element was by playing back the sound.
- the search result is recorded on the recording medium.
- the search result may be recorded in a memory managed by the control unit in correspondence with the recording medium.
- the search element is described as being registered in the memory in advance or used separately.
- the user searches the audio signal for the search element.
- the specified audio signal can be searched using the specified search element. In that case, it is not necessary to register the search element in advance.
- search element memory it is not necessary to extract the search element registered in the search element memory from the input sound signal or the reproduced sound signal.
- a sound source it is possible to prepare a sound source to be used as a search element and register the search element using an acoustic signal from the sound source.
- an acoustic signal and an acoustic feature parameter can be registered as a search element through a network such as an in-net network and register it in the search memory.
- search element candidates may be recorded together in advance in the recording medium. Further, when the recording medium is sold, a memory card storing the search element candidates may be added and sold.
- the input signal to be searched is an audio signal alone, but the audio signal is converted to a video signal.
- audio and video signals that are linked and related Input signal.
- FIG. 16 is a block diagram showing a configuration example in a case where the audio-video search device and the audio-video storage device according to the present embodiment are applied to a recording / reproduction device that records and reproduces an audio-video signal compressed according to the MPEG2 standard. is there.
- the recording / reproducing apparatus shown in FIG. 1 compresses and encodes video signals and audio signals according to the MPEG2 standard and multiplexes them as a transport stream (TS) of an MPEG system. This is a case where recording is made on a hard disk in a hard disk drive (HDD: Hard Disk Drive) and played back from the hard disk.
- HDD Hard Disk Drive
- analog video signals and analog audio signals are referred to as video signals and audio signals
- digital video signals and digital audio signals are referred to as digital video data and digital audio data, or simply video data and audio data. It will be referred to as Acoustic Sound.
- the recording / reproducing device 70 is connected to an antenna 61 for receiving an analog television broadcast, an analog input terminal 7 IV, 71 A, 71 S, an analog output terminal 72 V, 72 A, 72 S, and a digital input / output.
- Terminal 73 Digital interface 74, Input processor 80, Output processor 90, Multiplexer / Demultiplexer 100, Buffer controller 110, Hard disk drive 120, Synchronous control circuit 130, System controller 140, Sound search processor 150, and an operation input unit 160.
- the hard disk drive 120 includes three hard disks 121, 122, and 123, in which a transport stream is recorded, and a transport stream is transmitted from any of them. It is configured to be played.
- the system controller 140 has a CPU (Central Processing Unit) 141, and a ROM (Read Only Memory) 143 and 1 ⁇ AM (Random Access Memory) 144 and the like are connected to a system bus 142 thereof. Be composed.
- CPU Central Processing Unit
- ROM Read Only Memory
- AM Random Access Memory
- a program to be executed by the CPU 141 is stored in the ROM 143 in advance, and the CPU 141 reads the program and controls each unit of the recording / reproducing device 70.
- the RAMI 44 In the RAMI 44, other programs and data necessary for the CPU 141 to control each part of the recording / reproducing device 70 are written as appropriate.
- the operation input unit 160 includes a keyboard, a mouse, a button, a switch, a remote commander, and the like, and is connected to the system bus 142 of the system controller 140 via an input / output interface (not shown).
- the acoustic search processing unit 150 is a part configured to have any of the functions of the first to fifth embodiments described above.
- the case of the third embodiment is preferable as described above.
- the recording medium 13 uses the hard disk of the hard disk device 120. Therefore, the storage unit 12 or 42, the reproduction unit 14 or 44, and the like are constituted by the buffer controller 110. Therefore, in the figures of each of the above-described embodiments, the sound detection except for the recording and reproduction of the sound data as the main data is performed.
- the acoustic search processing unit 150 is configured by a part that performs the search processing.
- the searcher memory 32 can be provided in the sound searcher processing unit 150, or a part of the hard disk of the hard disk device 120 can be used.
- the frame number file is used as linked address information indicating the relevant section for search or registration.
- Field number, PTS (Present at ion Time Stamp), bucket number, etc. are used.
- the analog television broadcast signal received by the antenna 61 is selected by the tuner 81 according to the instruction of the system controller 140 based on the operation of the operation input unit 160, and the channel selected by the tuner 81 is selected.
- the composite video signal and the audio signal are obtained, and the composite video signal and the audio signal are supplied to one input terminal of the input switching circuit 82.
- a composite video signal from an external device is input to the input terminal 7IV, an audio signal is input from the external device to the input terminal 71A, and a separate video signal (luminance signal and color difference signal) is input to the input terminal 71S from the external device. ) Are supplied respectively.
- the composite video signal from the input terminal 7 IV and the audio signal from the input terminal 71 A are supplied to the other input terminal of the input switching circuit 82, and the input switching circuit 82 is switched by the system controller 140 to switch the input. From the circuit 82, one of the composite video signal and the audio signal is selected and taken out.
- the composite video signal from the input switching circuit 82 is separated into a luminance signal and a color difference signal by a YC separation circuit 83 and supplied to one input terminal of another input switching circuit 84. Further, a separate video signal (luminance signal and color difference signal) from the input terminal 71 S is supplied to the other input terminal of the input switching circuit 84, and the input switching circuit 84 is switched by the system controller 140, and the input switching is performed. From the circuit 84, one of the luminance signal and the color difference signal is selected and taken out.
- the luminance signal and the color difference signal from the input switching circuit 84 are A / D (Analogto Digita 1) converted by an NTSC (National Television System on Computer System) decoder 85, respectively. Further, it is chroma-encoded and the component video data is obtained from the NTSC decoder 85.
- NTSC National Television System on Computer System
- a vertical synchronizing signal and a horizontal synchronizing signal are separated from the luminance signal from the input switching circuit 84, and a clock and a field discrimination signal are generated based on the separated synchronizing signal.
- the synchronization signal, the clock, and the field determination signal are supplied to the synchronization control circuit 130.
- the synchronization control circuit 130 generates a clock and a timing signal necessary for each section of the recording / reproducing apparatus 70 based on these signals, and supplies the generated clock and timing signals to each section of the recording / reproducing apparatus 70.
- the video data from the NTSC decoder 85 is subjected to processing such as pre-filling processing in a pre-video processing circuit 86, and then supplied to an MPEG video encoder 87 and a lost video processing circuit 92 in an output processing unit 90.
- processing such as pre-filling processing in a pre-video processing circuit 86
- MPEG video encoder 87 the video data from the pre-video processing circuit 86 is subjected to encoding processing such as block DCT (Discrete Cosine Tran sfo rm), and the video elementary stream is processed.
- ES Elementary Stream
- the video elementary stream is supplied to the multiplexer Z demultiplexer 100.
- the audio signal from the input switching circuit 82 is converted into a digital audio signal by the / 0 converter 88, and then supplied to the MPEG audio encoder 89 and the output switching circuit 95 of the output processing unit 90.
- the audio data from the A / D converter 88 is compression-coded by the MPEG method to generate an audio elementary stream, and the audio elementary stream is multiplexed into a multiplexer multiplexer. Supplied to 100.
- the multiplexer / demultiplexer 100 in the multiplexer, the video elementary stream from the MPEG video encoder 87 and the audio elementary stream from the MPEG audio encoder 89 are multiplexed and various control signals are multiplexed. A transport stream of the system is generated, and the transport stream is sent to the buffer controller 110.
- the buffer controller 110 intermittently sends the transport stream continuously input from the multiplexer / demultiplexer 100 to the hard disk drive 120. That is, since writing cannot be performed when the hard disk drive 120 is performing a seek operation, the input transport stream is temporarily stored in a buffer, and when the hard disk drive 120 is writable, The transport stream is read out from the buffer at a higher rate than the incoming stream and sent to the hard disk device 120. Thus, the trans- port stream continuously input to the sofa controller 110 is recorded on the hard disks 121 to 123 without interruption.
- the hard disk drive 120 is controlled by the system controller 140 to write a transport stream to the hard disks 121 to 123.
- a protocol interface
- an IDE internal interface
- the hard disk device 120 is controlled by the system controller 140 to read a transport stream from the hard disks 121 to 123 and send it to the buffer controller 110.
- the buffer controller 110 converts the transport stream intermittently input from the hard disk drive 120 into a continuous transport stream and supplies the continuous stream to the multiplexer / demultiplexer 100, contrary to the case of recording. I do.
- the demultiplexer analyzes the header of the continuous transport stream, thereby converting the transport stream to a packetized elementary stream (PES). It is separated and supplied to the MPEG video / audio decoder 91.
- PES packetized elementary stream
- the MPEG video / audio decoder 91 has a multiplexer / demultiplexer.
- the PES from Plexa 100 is separated into a video elementary stream and an audio elementary stream, and the video elementary stream is decoded by an MPEG video decoder and converted to baseband video data.
- the audio elementary stream is decoded by the MPEG audio decoder and converted to a base-spanned audio data stream.
- the converted video data is supplied to a boost video processing circuit 92, and the audio data is supplied to an output switching circuit 95.
- the lost video processing circuit 92 switches or synthesizes the video data from the MPEG video / audio decoder 91 and the video data from the pre-video processing circuit 86 according to the instructions of the system controller 140. And processing such as a post-fill ring processing.
- the post-video processing circuit 92 also generates a representative screen (still image) for a GUI (Graphic ca 1 User Center), reduces a plurality of representative screens, and pastes them into a window.
- Image display processing is performed, and the processed image data is supplied to an OSD (On Screen Disp 1 ay) processing circuit 93.
- Representative screens include, for example, one characteristic scene from the program title, and a screen of the program's index point (one scene) to enable quick access to the desired scene in the program. is there.
- the OSD processing circuit 93 generates image data corresponding to text information and the like in accordance with an instruction from the system controller 140, and outputs the image data of the above window portion of the image data from the boost image processing circuit 92.
- the video data after the processing is supplied to the NTSC encoder 34.
- Multiple images displayed as reduced still images Figure 17 shows an example of the front screen. In the example of FIG. 17, 16 reduced still images 200 are pasted and displayed on the window.
- the video data (component video data) from the 0 SD processing circuit 93 is converted into a luminance data and a color difference data, or is not converted. As they are, they are D / A (Digital to Ana 1 og) converted, and separate video signals and composite video signals of analog signals are generated respectively.
- the separate video signal is led to an output terminal 72S, and the composite video signal is led to an output terminal 72V.
- the output switching circuit 95 either the audio data from the MPEG video / audio decoder 91 or the audio data from the AZD converter 88 is selected by the system controller 140. It is taken out. The selected audio data is converted into an analog audio signal by the D / A converter 36 and is output to the output terminal 72A.
- the separate video signal output to the output terminal 72 S, the composite video signal output to the output terminal 72 V, and the audio signal output to the output terminal 72 A are used to monitor external television receivers. By being output to the device 2, an image is displayed and sound is output on the monitor device 2.
- the recording / reproducing device 70 has a digital input / output terminal 74 connected between the digital input / output terminal 73 and the multiplexer / demultiplexer 100, and is connected to the digital input / output terminal 73.
- the transport stream input from the external device 63 is recorded on the hard disks 121 to 123, and The transport stream reproduced from the disks 121 to 123 is configured to be output to the external device 63.
- the external device 63 a device such as an IRD (IntegrateredRecceivverDecoder) or a personal computer can be connected.
- the digital interface 74 an IEEE 1394 (Institut eof Electronical and Electronics Encoders) 1394 digital interface is used, and the external device 63, the digital input / output terminal 73, The IEEE 1394 serial bus is used as the serial bus 64 for connecting the I / O.
- the transport stream input from the external device 63 to the digital input / output terminal 73 via the serial path 64 is interface-processed by the digital interface 74, sent to the multiplexer / demultiplexer 100, and sent to the multiplexer / demultiplexer 100. Is sent to the buffer controller 110 and is recorded on the hard disks 121 to 123 by the hard disk device 120. At the same time, the PES is separated from the transport stream to be recorded by the demultiplexer of the multiplexer / demultiplexer 100 and supplied to the MPEG video / audio decoder 91, so that the output terminals 72 V, 72 S And 72 A, an analog video signal and an analog audio signal can be obtained.
- the transport stream is read from the hard disk 12 1 to 123 by the hard disk device 120, and the reproduced transport stream is sent to the buffer controller 110, and the buffer controller 110 Multiplex from 1 1 0
- the signal is sent to the digital / demultiplexer 100, is subjected to interface processing at the digital input / output interface 74, is output to the digital input / output terminal 73, and is transmitted from the digital input / output terminal 73 to the serial bus 64.
- the image is displayed on the monitor device 7 connected to the external device 63 via the external device 63, and the sound is output.
- the PES is separated from the reproduced transport stream by the demultiplexer of the multiplexer / demultiplexer 100 and supplied to the MPEG video / audio decoder 91, so that the output terminals 72 V, 7 At 2S and 72A, a reproduced analog video signal and a reproduced analog audio signal can be obtained.
- sound search can be performed by the sound search processing unit 150 in the same manner as in the above-described first to fifth embodiments.
- the audio signal of the part searched by specifying the specific searcher sound parameter and the video signal part corresponding to the searched sound signal part are obtained from the link relationship between the two.
- the audio signal to be searched may be not only audio data recorded in the hard disk device 120 but also received or input audio data.
- the other input audio data A search is performed for the audio signal in the video signal, and the image portion of the search result is displayed, for example, in a sub-screen (sub-picture).
- the screen may be displayed only when it is searched, or may be displayed at all times.) Alternatively, the screen may be displayed on a part of the parent screen being viewed. This function can be used, for example, to use the voiceprint of a favorite actor as a search parameter for an acoustic parameter, and to convey the scene that the actor appears on the inset screen.
- the searcher acoustic feature parameters are registered in advance, and the user can select one of the reduced still images 200 as a searcher.
- an acoustic search operation using the searcher acoustic feature parameters corresponding to the instructed still image 200 may be performed.
- a specific person is displayed in the reduced still image, and the voiceprint of the person is stored in the searcher memory as the searcher acoustic feature parameters, and the reduced still image of the person is searched.
- a sound search process can be performed to extract a scene in which the person appears and speaks out. In this way, by registering the search acoustic feature parameters in correspondence with the reduced still image, the reduced still image can be used as an index for search.
- the scene searched for that searcher acoustic feature parameter is registered as a reduced still image used for reduced still image display. It can also be. For example, a scene in which a person is not shown but includes acoustic features such as a voiceprint of a specific person can be registered as the reduced still image.
- searcher acoustic signal and the searcher acoustic feature parameters can be provided as data superimposed on the broadcast signal.
- the user From the provided search elements, a desired one is selected and used for the search.
- necessary search element acoustic signals and search element acoustic feature parameters from the provided elements are stored in the search element memory 3 2 It can be registered and saved in.
- a search is performed only for an audio signal using a search element.
- the search is similarly performed for the video signal.
- a search child video feature parameter consisting of video feature parameters representing image features is registered for video signal search.
- the feature amount of the video to be extracted as the search child video feature parameter for example, luminance and its change, hue and its change, an image of a person or an object, and its change can be used.
- This search child video feature parameter can be obtained by analyzing the video signal of the section specified by the user from the input audio / video signals in the same manner as the search child audio feature parameter.
- a video signal consisting of a video portion serving as a searcher may be separately input and analyzed.
- the video feature parameters obtained by analyzing the video signal to be searched are compared with the video feature parameters of the searched child, and the similarity between the two is calculated.
- search for sound signals A predetermined portion is searched from the input audio / video signal based on a result and a search result for the video signal.
- the search parameter video feature parameter and the search parameter audio feature parameter may be registered as separate search elements and used separately, or registered in association with each other. You may use it.
- the search can be performed by individually designating both the search child video feature parameter and the search child acoustic feature parameter.
- a search element can be designated so as to use the search element video feature parameters and the search element acoustic feature parameters that are associated with each other.
- the searched portion may be displayed as address information or the like.
- the first scene of the searched portion may be displayed as the reduced still image. It may be.
- the signal portion of the search result may be sequentially reproduced.
- the search result and the search element are stored in the memory in association with each other, and the search element is relied on. Alternatively, the data can be read out and reproduced at a later time.
- the detection of the scene section using the video feature and the detection of the scene section using the acoustic feature are used together to obtain the search result.
- Scene sections can be meaningful. For example, even if a scene changes in terms of video, a scene that continues acoustically, such as a narration, can be detected without being separated by a change point in the video.
- the overlapping part of similar parts searched by the search child video feature parameter and the search child acoustic feature parameter is extracted.
- a sound signal to be searched and a sound signal as a search element are each analyzed over the acoustic feature parameters, and the acoustic feature parameters are compared with each other.
- search elements for search elements selected from the registered ones can be easily performed.
- search elements for search elements selected from the registered ones can be easily performed.
- a search for a search element prepared in advance can be performed for an audio signal to be searched.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Indexing, Searching, Synchronizing, And The Amount Of Synchronization Travel Of Record Carriers (AREA)
- Reverberation, Karaoke And Other Acoustics (AREA)
Description
Claims
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP00955045A EP1132890B1 (en) | 1999-08-26 | 2000-08-25 | Information retrieving/processing method, retrieving/processing device, storing method and storing device |
KR1020017005244A KR100782286B1 (ko) | 1999-08-26 | 2000-08-25 | 정보의 검색 처리 방법, 검색 처리 장치, 저장 방법 및저장 장치 |
DE60038535T DE60038535T2 (de) | 1999-08-26 | 2000-08-25 | Verfahren und vorrichtung, speicherverfahren und - vorrichtung zur informationsbeschaffung und verarbeitung |
US09/830,222 US7260226B1 (en) | 1999-08-26 | 2000-08-25 | Information retrieving method, information retrieving device, information storing method and information storage device |
US11/656,402 US8165306B2 (en) | 1999-08-26 | 2007-01-23 | Information retrieving method, information retrieving device, information storing method and information storage device |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP23914599 | 1999-08-26 | ||
JP11/239145 | 1999-08-26 |
Related Child Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/830,222 A-371-Of-International US7260226B1 (en) | 1999-08-26 | 2000-08-25 | Information retrieving method, information retrieving device, information storing method and information storage device |
US11/656,402 Division US8165306B2 (en) | 1999-08-26 | 2007-01-23 | Information retrieving method, information retrieving device, information storing method and information storage device |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2001016935A1 true WO2001016935A1 (fr) | 2001-03-08 |
Family
ID=17040435
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2000/005771 WO2001016935A1 (fr) | 1999-08-26 | 2000-08-25 | Procede et dispositif d'extraction/traitement d'informations, et procede et dispositif de stockage |
Country Status (6)
Country | Link |
---|---|
US (2) | US7260226B1 (ja) |
EP (2) | EP1132890B1 (ja) |
KR (1) | KR100782286B1 (ja) |
CN (1) | CN1178201C (ja) |
DE (1) | DE60038535T2 (ja) |
WO (1) | WO2001016935A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893431A (zh) * | 2015-12-09 | 2016-08-24 | 乐视网信息技术(北京)股份有限公司 | 媒体检索方法及设备 |
Families Citing this family (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2001016935A1 (fr) * | 1999-08-26 | 2001-03-08 | Sony Corporation | Procede et dispositif d'extraction/traitement d'informations, et procede et dispositif de stockage |
US7620545B2 (en) * | 2003-07-08 | 2009-11-17 | Industrial Technology Research Institute | Scale factor based bit shifting in fine granularity scalability audio coding |
JP3876855B2 (ja) * | 2003-07-10 | 2007-02-07 | ヤマハ株式会社 | オートミックスシステム |
US7738664B2 (en) * | 2003-10-07 | 2010-06-15 | Kddi Corporation | Apparatus for fault detection for parallelly transmitted audio signals and apparatus for delay difference detection and adjustment for parallelly transmitted audio signals |
GB0502844D0 (en) * | 2005-02-11 | 2005-03-16 | Univ Edinburgh | Storing digital content for access using a captured image |
WO2006100980A1 (ja) * | 2005-03-18 | 2006-09-28 | Pioneer Corporation | 音声信号処理装置及びそのためのコンピュータプログラム |
US7974420B2 (en) * | 2005-05-13 | 2011-07-05 | Panasonic Corporation | Mixed audio separation apparatus |
KR100782825B1 (ko) * | 2005-12-01 | 2007-12-06 | 삼성전자주식회사 | 오디오 컨텐츠 선택 정보 제공 방법 및 장치와 그 방법을수행하는 프로그램이 기록된 기록매체 |
CN101213589B (zh) * | 2006-01-12 | 2011-04-27 | 松下电器产业株式会社 | 对象声音分析装置和对象声音分析方法 |
JP4527679B2 (ja) * | 2006-03-24 | 2010-08-18 | 学校法人早稲田大学 | 音声の類似度の評価を行う方法および装置 |
JP2008154143A (ja) * | 2006-12-20 | 2008-07-03 | Sony Corp | 受信データ記録システム、受信機、受信機の制御方法、レコーダ、データ記録方法およびプログラム |
US20100319015A1 (en) * | 2009-06-15 | 2010-12-16 | Richard Anthony Remington | Method and system for removing advertising content from television or radio content |
WO2011041008A1 (en) * | 2009-10-01 | 2011-04-07 | Richard Anthony Remington | Method for removing advertising content |
JP5568953B2 (ja) * | 2009-10-29 | 2014-08-13 | ソニー株式会社 | 情報処理装置、シーン検索方法及びプログラム |
JP2011199847A (ja) * | 2010-02-25 | 2011-10-06 | Ricoh Co Ltd | 会議システムの端末装置、会議システム |
JP5333517B2 (ja) * | 2011-05-26 | 2013-11-06 | ヤマハ株式会社 | データ処理装置およびプログラム |
CN102522084B (zh) * | 2011-12-22 | 2013-09-18 | 广东威创视讯科技股份有限公司 | 一种将语音数据转换为文本文件的方法和系统 |
CN103390409A (zh) * | 2012-05-11 | 2013-11-13 | 鸿富锦精密工业(深圳)有限公司 | 电子装置及其侦测色情音频的方法 |
CN103116494B (zh) * | 2013-01-25 | 2016-05-25 | 中兴通讯股份有限公司 | 自动化测试平台测试输出信息提取方法和装置 |
KR102184987B1 (ko) * | 2013-11-15 | 2020-12-01 | 엘지전자 주식회사 | 영상 표시 장치 및 그 동작 방법 |
KR102255152B1 (ko) * | 2014-11-18 | 2021-05-24 | 삼성전자주식회사 | 가변적인 크기의 세그먼트를 전송하는 컨텐츠 처리 장치와 그 방법 및 그 방법을 실행하기 위한 컴퓨터 프로그램 |
CN106682505B (zh) * | 2016-05-04 | 2020-06-12 | 腾讯科技(深圳)有限公司 | 一种病毒检测方法、终端、服务器及系统 |
WO2020218075A1 (ja) * | 2019-04-26 | 2020-10-29 | ソニー株式会社 | 情報処理装置および方法、並びにプログラム |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05334861A (ja) * | 1992-06-03 | 1993-12-17 | Japan Radio Co Ltd | 音声検索装置 |
JPH07105235A (ja) * | 1993-10-08 | 1995-04-21 | Sharp Corp | 画像検索方法及び画像検索装置 |
JPH08265660A (ja) * | 1995-03-20 | 1996-10-11 | Nippon Telegr & Teleph Corp <Ntt> | 音楽管理方法および装置 |
JPH099199A (ja) * | 1995-06-19 | 1997-01-10 | Sony Corp | 映像信号記録/再生装置 |
JPH10307580A (ja) * | 1997-05-06 | 1998-11-17 | Nippon Telegr & Teleph Corp <Ntt> | 音楽検索方法および装置 |
JPH10319948A (ja) * | 1997-05-15 | 1998-12-04 | Nippon Telegr & Teleph Corp <Ntt> | 音楽演奏に含まれる楽器音の音源種類判別方法 |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2791036B2 (ja) * | 1988-04-23 | 1998-08-27 | キヤノン株式会社 | 音声処理装置 |
JP3171744B2 (ja) | 1994-03-15 | 2001-06-04 | シャープ株式会社 | 音声及び動画の検索装置 |
JP3664499B2 (ja) | 1994-08-16 | 2005-06-29 | 富士通株式会社 | 音声情報の処理方法及びその装置 |
JPH09106339A (ja) | 1995-10-11 | 1997-04-22 | Toshiba Corp | 情報処理装置およびデータ格納方法 |
WO2001016935A1 (fr) * | 1999-08-26 | 2001-03-08 | Sony Corporation | Procede et dispositif d'extraction/traitement d'informations, et procede et dispositif de stockage |
JP4438144B2 (ja) * | 1999-11-11 | 2010-03-24 | ソニー株式会社 | 信号分類方法及び装置、記述子生成方法及び装置、信号検索方法及び装置 |
EP1244093B1 (en) * | 2001-03-22 | 2010-10-06 | Panasonic Corporation | Sound features extracting apparatus, sound data registering apparatus, sound data retrieving apparatus and methods and programs for implementing the same |
US7738664B2 (en) * | 2003-10-07 | 2010-06-15 | Kddi Corporation | Apparatus for fault detection for parallelly transmitted audio signals and apparatus for delay difference detection and adjustment for parallelly transmitted audio signals |
US20060195322A1 (en) * | 2005-02-17 | 2006-08-31 | Broussard Scott J | System and method for detecting and storing important information |
-
2000
- 2000-08-25 WO PCT/JP2000/005771 patent/WO2001016935A1/ja active IP Right Grant
- 2000-08-25 US US09/830,222 patent/US7260226B1/en not_active Expired - Fee Related
- 2000-08-25 DE DE60038535T patent/DE60038535T2/de not_active Expired - Lifetime
- 2000-08-25 KR KR1020017005244A patent/KR100782286B1/ko not_active IP Right Cessation
- 2000-08-25 EP EP00955045A patent/EP1132890B1/en not_active Expired - Lifetime
- 2000-08-25 EP EP07022741A patent/EP1887561A3/en not_active Withdrawn
- 2000-08-25 CN CNB008022186A patent/CN1178201C/zh not_active Expired - Fee Related
-
2007
- 2007-01-23 US US11/656,402 patent/US8165306B2/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05334861A (ja) * | 1992-06-03 | 1993-12-17 | Japan Radio Co Ltd | 音声検索装置 |
JPH07105235A (ja) * | 1993-10-08 | 1995-04-21 | Sharp Corp | 画像検索方法及び画像検索装置 |
JPH08265660A (ja) * | 1995-03-20 | 1996-10-11 | Nippon Telegr & Teleph Corp <Ntt> | 音楽管理方法および装置 |
JPH099199A (ja) * | 1995-06-19 | 1997-01-10 | Sony Corp | 映像信号記録/再生装置 |
JPH10307580A (ja) * | 1997-05-06 | 1998-11-17 | Nippon Telegr & Teleph Corp <Ntt> | 音楽検索方法および装置 |
JPH10319948A (ja) * | 1997-05-15 | 1998-12-04 | Nippon Telegr & Teleph Corp <Ntt> | 音楽演奏に含まれる楽器音の音源種類判別方法 |
Non-Patent Citations (6)
Title |
---|
H. SOLTAU ET AL.: "Recognition of music types", PROCEEDINGS OF 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, vol. 2, 12 May 1998 (1998-05-12) - 15 May 1998 (1998-05-15), pages 1137 - 1140, ISBN0-7803-4428-6, IEEE CAT. NO. 98CH36181, XP002933355 * |
K. MELIH ET AL.: "Audio source type segmentation using a perceptually based representation", PROCEEDINGS OF THE FIFTH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, ISSPA'99, vol. 1, 22 August 1999 (1999-08-22) - 25 August 1999 (1999-08-25), pages 51 - 54, ISBN1-86435-451-8, IEEE CAT. NO. 99EX359, XP002933356 * |
KUNIO KASHIWANO ET AL.: "note recognition mechanisms in the OPTIMA processing architecture for music scene analysis", TRANSACTIONS OF THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS, vol. J79-D-II, no. 11, 25 November 1996 (1996-11-25), pages 1751 - 1761, ISSN0915-1923, XP002933357 * |
KUNIO KASHIWANO ET AL.: "Sound source identification using adaptive template mixtures - Formulation and application to music stream segregation", IPSJ SIG NOTES (SIGMUS), vol. 97, no. 18, 20 February 1997 (1997-02-20), pages 55 - 60, 97-MUS-19-11, ISSN0919-6072, XP002933358 * |
See also references of EP1132890A4 * |
T. LAMBROU ET AL.: "Classification of audio signal using statistical features on time and wavelet transform domains", PROCEEDINGS OF 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, vol. 6, 12 May 1998 (1998-05-12) - 15 May 1998 (1998-05-15), pages 3621 - 3624, ISBN0-7803-4428-6, IEEE CAT. NO. 98CH36181, XP002933354 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893431A (zh) * | 2015-12-09 | 2016-08-24 | 乐视网信息技术(北京)股份有限公司 | 媒体检索方法及设备 |
Also Published As
Publication number | Publication date |
---|---|
CN1178201C (zh) | 2004-12-01 |
DE60038535D1 (de) | 2008-05-21 |
US7260226B1 (en) | 2007-08-21 |
KR20010089358A (ko) | 2001-10-06 |
KR100782286B1 (ko) | 2007-12-07 |
US20070127735A1 (en) | 2007-06-07 |
EP1887561A3 (en) | 2008-07-02 |
CN1327573A (zh) | 2001-12-19 |
EP1132890A4 (en) | 2005-08-17 |
EP1132890B1 (en) | 2008-04-09 |
US8165306B2 (en) | 2012-04-24 |
EP1132890A1 (en) | 2001-09-12 |
DE60038535T2 (de) | 2009-07-02 |
EP1887561A2 (en) | 2008-02-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8165306B2 (en) | Information retrieving method, information retrieving device, information storing method and information storage device | |
JP4491700B2 (ja) | 音響検索処理方法、音響情報検索装置、音響情報蓄積方法、音響情報蓄積装置および音響映像検索処理方法、音響映像情報検索装置、音響映像情報蓄積方法、音響映像情報蓄積装置 | |
JP4584250B2 (ja) | 映像処理装置、映像処理装置の集積回路、映像処理方法、及び映像処理プログラム | |
CN101534407B (zh) | 信息记录装置 | |
JP3615195B2 (ja) | コンテンツ記録再生装置およびコンテンツ編集方法 | |
JP4442585B2 (ja) | 楽曲区間検出方法、及びその装置、並びにデータ記録方法、及びその装置 | |
WO2000036833A1 (fr) | Procede et appareil permettant de retrouver vocalement des scenes video ou audio | |
WO2007074755A1 (ja) | 楽曲区間検出方法、及びその装置、並びにデータ記録方法、及びその装置 | |
JP4513165B2 (ja) | 番組記録方法及び番組記録装置及び番組記録再生装置及び番組記録再生方法 | |
JPWO2007046171A1 (ja) | 記録再生装置 | |
JP4913288B2 (ja) | 情報信号処理装置及び情報信号処理方法 | |
KR101230746B1 (ko) | 음악데이터와 동시 출력을 위한 동기화된 영상데이터 생성방법과 그 동기화 출력을 위한 재생 방법 | |
US6285982B1 (en) | Sound decompressing apparatus providing improved sound quality during special reproducing such as forward search reproducing and reverse search reproducing | |
JP2006054517A (ja) | 情報提示装置、方法及びプログラム | |
JP2001298711A (ja) | 画像記録再生装置および方法、並びに記録媒体 | |
JP4287243B2 (ja) | 放送番組記録装置、放送番組再生装置、放送番組記録再生装置及び放送番組記録再生方法 | |
KR20050054937A (ko) | 시청각 데이터 스트림을 메모리에 저장하는 방법 | |
JPH08205044A (ja) | 情報提供制御装置及び情報提供制御方法 | |
JP2007081899A (ja) | 広告情報処理装置 | |
JP5188619B2 (ja) | 情報記録装置 | |
JP2000092435A (ja) | 信号特徴抽出方法及びその装置、音声認識方法及びその装置、動画編集方法及びその装置 | |
JP2004072306A (ja) | ビデオカメラ及びビデオ再生装置 | |
JP2006254257A (ja) | 視聴制限装置 | |
JP2006333340A (ja) | 情報再生装置、情報再生方法及びコンピュータプログラム | |
JP2006286031A (ja) | コンテンツ再生装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 00802218.6 Country of ref document: CN |
|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): CN KR US |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1020017005244 Country of ref document: KR |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2000955045 Country of ref document: EP |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 09830222 Country of ref document: US |
|
WWP | Wipo information: published in national office |
Ref document number: 2000955045 Country of ref document: EP |
|
WWP | Wipo information: published in national office |
Ref document number: 1020017005244 Country of ref document: KR |
|
WWG | Wipo information: grant in national office |
Ref document number: 2000955045 Country of ref document: EP |