Automatic identification of repeated material in audio signals
AssigneeShazam Investments Limited
InventorsDavid L. DeBusk, Darren P. Briggs, Michael Karliner, Richard W. Cheong Tang, Avery Li-Chun Wang
Life of this patent
Estimating the term…
Abstract
A system and method are described for recognizing repeated audio material within at least one media stream without prior knowledge of the nature of the repeated material. The system and method are able to create a screening database from the media stream or streams. An unknown sample audio fragment is taken from the media stream and compared against the screening database to find if there are matching fragments within the media streams by determining if the unknown sample matches any samples in the screening database.
Claims29
A method comprising:
- receiving, at a computing device, a segment of non-recognized data from a media stream, wherein the non-recognized data comprises unknown content;
- determining whether the segment of non-recognized data matches previous non-recognized data from one or more media streams so as to identify repeated portions of non-recognized content, wherein the one or more media streams includes the media stream;
- determining a count of the repeated portions of non-recognized content in the one or more media streams;
- and
- providing, by the computing device, the segment of non-recognized data for content identification based on the count of the repeated portions of non-recognized content in the one or more media streams exceeding a threshold.
A non-transitory computer readable memory having stored thereon instructions executable by a computing device to cause the computing device to perform functions comprising:
- receiving a segment of non-recognized data from a media stream, wherein the non-recognized data comprises unknown content;
- determining whether the segment of non-recognized data matches previous non-recognized data from one or more media streams so as to identify repeated portions of non-recognized content, wherein the one or more media streams includes the media stream;
- determining a number of the repeated portions of non-recognized content in the one or more media streams;
- and
- providing the segment of non-recognized data for content identification based on the number of the repeated portions of non-recognized content in the one or more media streams exceeding a threshold.
A method comprising:
- receiving, at a computing device, a segment of non-recognized data from a media stream, wherein the non-recognized data comprises unknown content;
- determining whether the segment of non-recognized data matches previous non-recognized data from one or more media streams so as to identify repeated portions of non-recognized content, wherein the one or more media streams includes the media stream;
- determining a number of the repeated portions of non-recognized content in the one or more media streams;
- determining that the number of the repeated portions of non-recognized content in the one or more media streams exceeds a threshold;
- and
- based on the number of the repeated portions of non-recognized content in the one or more media streams exceeding the threshold, responsively indexing the segment of non-recognized data into a searchable database so as to create a screening database of unknown data from the one or more media streams.
A method comprising:
- performing a first content identification of one or more segments of data from the media stream;
- and
- determining, by a computing device, a segment of unknown data based on the first content identification of the one or more segments of data from the media stream resulting in unrecognized data;
- determining a number of times that the segment of unknown data repeats within one or more media streams;
- and
- providing, by the computing device, the segment of unknown data for a second content identification based on the number of times that the segment of unknown data repeats within the one or more media streams exceeding a threshold.
A method comprising:
- creating a screening database from at least one media stream, wherein the screening database includes samples of the at least one media stream;
- taking an unidentified sample from the at least one media stream;
- determining whether the unidentified sample matches previous data within the at least one media stream so as to identify repeated portions of content;
- determining a count of the repeated portions of content based on matches of the unidentified sample to any samples in the screening database;
- and
- providing the unidentified sample for content identification based on the count of the repeated portions of content exceeding a threshold.
Dependencies are inferred from the claim text.