Maxwell Wells - Seattle WA, US Vidya Venkatachalam - Bellevue WA, US Luca Cazzanti - Bellevue WA, US Kwan Fai Cheung - Bellevue WA, US Navdeep Dhillon - Seattle WA, US Somsak Sukittanon - Seattle WA, US
Assignee:
Gracenote, Inc. - Emeryville CA
International Classification:
G10L 11/00 G10L 15/00
US Classification:
704231, 704238, 704243, 704270, 704273
Abstract:
Copies of original sound recordings are identified by extracting features from the copy, creating a vector of those features, and comparing that vector against a database of vectors. Identification can be performed for copies of sound recordings that have been subjected to compression and other manipulation such that they are not exact replicas of the original. Computational efficiency permits many hundreds of queries to be serviced at the same time. The vectors may be less than 100 bytes, so that many millions of vectors can be stored on a portable device.
Maxwell Wells - Seattle WA, US Vidya Venkatachalam - Bellevue WA, US Luca Cazzanti - Bellevue WA, US Kwan Fai Cheung - Bellevue WA, US Navdeep Dhillon - Seattle WA, US Somsak Sukittanon - Seattle WA, US
Assignee:
Gracenote, Inc. - Emeryville CA
International Classification:
G10L 15/06
US Classification:
704243, 704245
Abstract:
Copies of original sound recordings are identified by extracting features from the copy, creating a vector of those features, and comparing that vector against a database of vectors. Identification can be performed for copies of sound recordings that have been subjected to compression and other manipulation such that they are not exact replicas of the original. Computational efficiency permits many hundreds of queries to be serviced at the same time. The vectors may be less than 100 bytes, so that many millions of vectors can be stored on a portable device.