Automatic identification of repeated material in audio signals
First Claim
Patent Images
1. A method of recognizing repeated audio material within at least one media stream without prior knowledge of the nature of the repeated material, comprising:
- receiving a sample audio fragment from the at least one media stream;
determining, via a processor, whether the sample audio fragment matches an entry in a database of known media samples, wherein the sample audio fragment is an unknown sample when the sample audio fragment does not match an entry in the database;
determining whether the unknown sample matches an unknown audio fragment indexed in a screening database;
recording a match between the unknown sample and the unknown audio fragment when, based on the determination, the unknown sample matches the unknown audio fragment;
determining whether the unknown sample is ready to be published for identification and inclusion into the database of known media samples based on repeated matches between the unknown sample and the unknown audio fragment; and
publishing the unknown sample for identification and inclusion into the database of known media samples when the repeated matches exceed a threshold.
3 Assignments
0 Petitions
Accused Products
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.
56 Citations
22 Claims
-
1. A method of recognizing repeated audio material within at least one media stream without prior knowledge of the nature of the repeated material, comprising:
-
receiving a sample audio fragment from the at least one media stream; determining, via a processor, whether the sample audio fragment matches an entry in a database of known media samples, wherein the sample audio fragment is an unknown sample when the sample audio fragment does not match an entry in the database; determining whether the unknown sample matches an unknown audio fragment indexed in a screening database; recording a match between the unknown sample and the unknown audio fragment when, based on the determination, the unknown sample matches the unknown audio fragment; determining whether the unknown sample is ready to be published for identification and inclusion into the database of known media samples based on repeated matches between the unknown sample and the unknown audio fragment; and publishing the unknown sample for identification and inclusion into the database of known media samples when the repeated matches exceed a threshold. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
-
15. A system for recognizing repeated segments of non-recognized media content in at least one source of non-recognized media content, the system comprising:
-
a database storing known media samples; a screening database storing non-recognized media segments received from the at least one source; a candidate manager receiving the non-recognized media after the non-recognized media has failed to match an entry in the database of known media samples, and associating an identifier with samples of the non-recognized media; a fingerprint generator operable to create fingerprints for non-recognized media segments; and a media search engine connected to the candidate manager and the fingerprint generator, the media search engine configured to; compare fingerprints of non-recognized media against the previously stored non-recognized media fingerprints in the screening database, record repeated matches of the non-recognized media within the screening database, determine if the non-recognized media is ready for publication for identification and inclusion into the database of known media samples based on whether the repeated matches in the screening database, and publish the unknown sample for identification and inclusion into the database of known media samples when the repeated matches exceed a threshold value. - View Dependent Claims (16, 17, 18, 19, 20, 21)
-
-
22. A method of recognizing repeated audio material within at least one media stream without prior knowledge of the nature of the repeated material, comprising:
-
receiving a sample audio fragment from the at least one media stream; determining, via a processor, whether the sample audio fragment is a non-recognized segment of audio (NRA) based on a comparison with a database of known media samples; creating a screening database from the at least one media stream, said screening database including previously-determined NRA'"'"'s; determining if the NRA matches one or more of the previously-determined NRA'"'"'s in the screening database; publishing the NRA for identification and inclusion into the database of known media samples when the matches between the NRA and the one or more of the previously-determined NRA'"'"'s exceeds a threshold value.
-
Specification