System for monitoring audio content in a video broadcast
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-017/00
G06F-017/17
G01R-023/16
H04H-009/00
G06G-007/00
출원번호
US-0895822
(2001-06-29)
발명자
/ 주소
Pitman,Michael C.
Fitch,Blake G.
Abrams,Steven
Germain,Robert S.
출원인 / 주소
International Business Machines Corporation
대리인 / 주소
Fleit, Kain, Gibbons, Gutman, Bongini &
인용정보
피인용 횟수 :
8인용 특허 :
8
초록▼
A method is provided for monitoring audio content in a video broadcast. According to the method, an audio datastream from the video broadcast is received, and audio identifying information is generated for audio content from the audio datastream. It is determined whether the audio identifying inform
A method is provided for monitoring audio content in a video broadcast. According to the method, an audio datastream from the video broadcast is received, and audio identifying information is generated for audio content from the audio datastream. It is determined whether the audio identifying information generated for the received audio content matches audio identifying information in an audio content database. In one preferred embodiment, the audio identifying information is an audio feature signature that is based on audio content. Also provided is a system for monitoring audio content in a video broadcast.
대표청구항▼
What is claimed is: 1. A method for monitoring audio content in a video broadcast, said method comprising the steps of: receiving an audio datastream from the video broadcast; generating audio identifying information for audio content from the audio datastream based on detected events in the audio
What is claimed is: 1. A method for monitoring audio content in a video broadcast, said method comprising the steps of: receiving an audio datastream from the video broadcast; generating audio identifying information for audio content from the audio datastream based on detected events in the audio content; and determining whether the audio identifying information generated for the received audio content matches audio identifying information in an audio content database, wherein the generating step includes the sub-step of: detecting a plurality of events in the audio content, each of the events being a crossing of the value of a first running average and the value of a second running average, wherein the first running average is an average over a first averaging period of a plurality of time dependent frequency components of the audio content, and the second running average is an average over a second averaging period, which is different than the first averaging period, of the time dependent frequency components of the audio content. 2. The method according to claim 1, wherein the audio identifying information is an audio feature signature that is based on the detected events in the audio content. 3. The method according to claim 2, wherein the determining step includes the sub-step of comparing the audio feature signature generated for the received audio content with the audio feature signatures stored in the audio content database. 4. The method according to claim 1, further comprising the steps of: generating audio identifying information for predetermined audio content based on detected events in the predetermined audio content; and storing the audio identifying information for the predetermined audio content in the audio content database. 5. The method according to claim 1, further comprising the step of: if the audio identifying information generated for the received audio content matches audio identifying information in the audio content database, recording information on a match between the received audio content and the audio content database. 6. The method according to claim 5, further comprising the steps of: compiling cue sheet entries from the recorded match information, the cue sheet entries including identification of at least one piece of audio content in the video broadcast, a start time of each piece of audio content, and a duration of each piece of audio content; and charging royalties based on the cue sheet entries. 7. The method according to claim 5, further comprising the steps of: compiling cue sheet entries from the recorded match information, the cue sheet entries including identification of each piece of audio content in the video broadcast, a start time of each piece of audio content, and a duration of each piece of audio content; and paying royalties based on the cue sheet entries. 8. The method according to claim 5, further comprising the step of: compiling a cue sheet containing cue sheet entries from the recorded match information, the cue sheet entries including identification of at least one piece of audio content in the video broadcast, a start time of each piece of audio content, and a duration of each piece of audio content; and charging a fee for the cue sheet. 9. The method according to claim 1, wherein the generating step further includes the sub-steps of: obtaining an audio signal characterized by a time dependent power spectrum; analyzing the spectrum to obtain the time dependent frequency components; producing the audio identifying information for the audio content from the audio datastream based on the detected events. 10. The method according to claim 9, wherein the sub-step of analyzing the spectrum includes: sampling the audio signal to obtain a plurality of audio signal samples; taking a plurality of subsets from the plurality of audio signal samples; and performing a Fourier transform on each of the plurality of subsets to obtain a set of Fourier frequency components. 11. The method according to claim 9, wherein the sub-step of detecting a plurality of events includes: keeping the first running average over the first averaging period of the plurality of time dependent frequency components so as to obtain a first series of averages for the first averaging period; keeping the second running average over the second averaging period of the plurality of time dependent frequency components so as to obtain a second series of averages for the first averaging period; and recording a plurality of event times, each of the event times being a time at which there occurs one of the detected events of the first running average crossing the second running average. 12. The method according to claim 1, wherein the generating step further includes the sub-steps of: performing a Fourier transformation of the audio content into a time series of audio power dissipated over a first plurality of frequencies; grouping the frequencies into a smaller second plurality of bands that each include a range of neighboring frequencies; detecting power dissipation events in each of the bands; and grouping together the power dissipation events from mutually adjacent bands at a selected moment so as to form an identifying feature. 13. A method for charging a royalty for usage of copyrighted audio content in a video broadcast, said method comprising the steps of: receiving an audio datastream from the video broadcast; generating audio identifying information for audio content from the audio datastream based on detected events in the audio content; determining whether the audio identifying information generated for the received audio content matches audio identifying information in a copyrighted audio content database; and if the audio identifying information generated for the received audio content matches audio identifying information in the copyrighted audio content database, determining a duration of the audio content in the video broadcast and charging a royalty based on the duration, wherein the generating step includes the sub-step of: detecting a plurality of events in the audio content, each of the events being a crossing of the value of a first running average and the value of a second running average, wherein the first running average is an average over a first averaging period of a plurality of time dependent frequency components of the audio content, and the second running average is an average over a second averaging period, which is different than the first averaging period, of the time dependent frequency components of the audio content. 14. A computer-readable medium encoded with a program for monitoring audio content in a video broadcast, said program containing instructions for performing the steps of: receiving an audio datastream from the video broadcast; generating audio identifying information for audio content from the audio datastream based on detected events in the audio content; and determining whether the audio identifying information generated for the received audio content matches audio identifying information in an audio content database, wherein the generating step includes the sub-step of: detecting a plurality of events in the audio content, each of the events being a crossing of the value of a first running average and the value of a second running average, wherein the first running average is an average over a first averaging period of a plurality of time dependent frequency components of the audio content, and the second running average is an average over a second averaging period, which is different than the first averaging period, of the time dependent frequency components of the audio content. 15. The computer-readable medium according to claim 14, wherein the audio identifying information is an audio feature signature that is based on the detected events in the audio content. 16. The computer-readable medium according to claim 15, wherein the determining step includes the sub-step of comparing the audio feature signature generated for the received audio content with the audio feature signatures stored in the audio content database. 17. The computer-readable medium according to claim 14, wherein said program further contains instructions for performing the steps of: generating audio identifying information for predetermined audio content based on detected events in the predetermined audio content; and storing the audio identifying information for the predetermined audio content in the audio content database. 18. The computer-readable medium according to claim 14, wherein said program further contains instructions for performing the step of: if the audio identifying information generated for the received audio content matches audio identifying information in the audio content database, determining a duration of the audio content in the video broadcast and charging a royalty based on the duration. 19. The computer-readable medium according to claim 14, wherein said program further contains instructions for performing the steps of: if the audio identifying information generated for the received audio content matches audio identifying information in the audio content database, recording information on a match between the received audio content and the audio content database; compiling cue sheet entries from the recorded match information, the cue sheet entries including identification of at least one piece of audio content in the video broadcast, a start time of each piece of audio content, and a duration of each piece of audio content; and charging royalties based on the cue sheet entries. 20. The computer-readable medium according to claim 14, wherein said program further contains instructions for performing the steps of: if the audio identifying information generated for the received audio content matches audio identifying information in the audio content database, recording information on a match between the received audio content and the audio content database; compiling cue sheet entries from the recorded match information, the cue sheet entries including identification of each piece of audio content in the video broadcast, a start time of each piece of audio content, and a duration of each piece of audio content; and paying royalties based on the cue sheet entries. 21. The computer-readable medium according to claim 14, wherein the generating step further includes the sub-steps of: obtaining an audio signal characterized by a time dependent power spectrum; analyzing the spectrum to obtain the time dependent frequency components; producing the audio identifying information for the audio content from the audio datastream based on the detected events. 22. The computer-readable medium according to claim 21, wherein the sub-step of analyzing the spectrum includes: sampling the audio signal to obtain a plurality of audio signal samples; taking a plurality of subsets from the plurality of audio signal samples; and performing a Fourier transform on each of the plurality of subsets to obtain a set of Fourier frequency components. 23. The computer-readable medium according to claim 21, wherein the sub-step of detecting a plurality of events includes: keeping the first running average over the first averaging period of the plurality of time dependent frequency components so as to obtain a first series of averages for the first averaging period; keeping the second running average over the second averaging period of the plurality of time dependent frequency components so as to obtain a second series of averages for the first averaging period; and recording a plurality of event times, each of the event times being a time at which there occurs one of the detected events of the first running average crossing the second running average. 24. The computer-readable medium according to claim 14, wherein the generating step further includes the sub-steps of: performing a Fourier transformation of the audio content into a time series of audio power dissipated over a first plurality of frequencies; grouping the frequencies into a smaller second plurality of bands that each include a range of neighboring frequencies; detecting power dissipation events in each of the bands; and grouping together the power dissipation events from mutually adjacent bands at a selected moment so as to form an identifying feature. 25. A system for monitoring audio content in a video broadcast, said system comprising: a receiver for receiving an audio datastream from the video broadcast; an identifying information generator for generating audio identifying information based on detected events in audio content from the audio datastream; and a match detector for determining whether the audio identifying information generated for the received audio content matches audio identifying information in an audio content database, wherein the identifying information generator detects a plurality of events in the audio content, each of the events being a crossing of the value of a first running average and the value of a second running average, the first running average is an average over a first averaging period of a plurality of time dependent frequency components of the audio content, and the second running average is an average over a second averaging period, which is different than the first averaging period of the time dependent frequency components of the audio content. 26. The system according to claim 25, wherein the audio identifying information is an audio feature signature that is based on the detected events in the audio content. 27. The system according to claim 25, wherein the audio content database stores audio identifying information for predetermined audio content. 28. The system according to claim 25, further comprising: an invoicer for determining a duration of the audio content in the video broadcast and charging a royalty based on the duration, if the audio identifying information generated for the received audio content matches audio identifying information in the audio content database. 29. The system according to claim 25, further comprising: an information collector for recording information on a match between the received audio content and the audio content database, if the audio identifying information generated for the received audio content matches audio identifying information in the audio content database; a cue sheet generator for compiling cue sheet entries from the recorded match information, the cue sheet entries including identification of at least one piece of audio content in the video broadcast, a start time of each piece of audio content, and a duration of each piece of audio content; and an invoicer for charging royalties based on the cue sheet entries. 30. The system according to claim 25, further comprising: an information collector for recording information on a match between the received audio content and the audio content database, if the audio identifying information generated for the received audio content matches audio identifying information in the audio content database; a cue sheet generator for compiling cue sheet entries from the recorded match information, the cue sheet entries including identification of each piece of audio content in the video broadcast, a start time of each piece of audio content, and a duration of each piece of audio content; and a royalty calculator for calculating royalties to be paid based on the cue sheet entries.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (8)
Reynolds Kentyn (Santa Fe NM), Method and apparatus for wave analysis and event recognition.
Ellis Michael D. (Boulder CO) Dunn Stephen M. (Boulder CO) Fellinger Michael W. (Boulder CO) Younglove Fancy B. (Boulder CO) James David M. (Fort Collins CO) Clifton David L. (Boulder CO) Land Richar, Method and system for recognition of broadcast segments.
Drosset, Joseph St-John; Kim, Michael; Bottorf, Christopher J.; McMillan, Juan C., Method and system for subscriber-based audio service over a communication network.
Walters, Thomas Chadwick; Halkes, Gertjan Pieter; Konrad, Matthias Rochus; Postelnicu, Gheorghe, Audio and video matching using a hybrid of fingerprinting and content based classification.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.