INTERVALGRAM REPRESENTATION OF AUDIO FOR MELODY RECOGNITION
摘要
A system, method, and computer readable storage medium generates an audio fingerprint for an input audio clip that is robust to differences in key, instrumentation, and other performance variations. The audio fingerprint comprises a sequence of intervalgrams that represent a melody in an audio clip according pitch intervals between different time points in the audio clip. The fingerprint for an input audio clip can be compared to a set of reference fingerprints in a reference database to determine a matching reference audio clip.
申请公布号
WO2012005970(A3)
申请公布日期
2012.03.29
申请号
WO2011US41681
申请日期
2011.06.23
申请人
GOOGLE INC.;LYON, RICHARD, F.;WALTERS, THOMAS, C.;ROSS, DAVID