System and method for selective removal of audio content from a mixed audio recording

摘要

Systems and techniques for removing a sound recording from an audio recording (e.g., an audio recording embedded in a media file) are presented. The system can include an identification component, a first subtraction component and a second subtraction component. The identification component identifies a sound recording in a mixed audio recording. The first subtraction component determines a local linear transformation of the sound recording and subtracts the local linear transformation of the sound recording from the mixed audio recording to generate a new mixed audio recording. The second subtraction component compares one or more segments of the sound recording with one or more corresponding segments of the new mixed audio recording and reduces a power level of the new mixed audio recording based at least in part on correlation of the one or more corresponding segments with the one or more segments.

主权项

1. A system, comprising:
a processor; and a memory communicatively coupled to the processor, the memory having stored therein computer-executable instructions, comprising:
an identification component configured to identify a reference sound recording, from a plurality of reference sound recordings, that matches a portion of a mixed audio recording;a first subtraction component configured to determine a local linear transformation of the reference sound recording to transform the reference sound recording that approximates the portion of the mixed audio recording and subtract the local linear transformation of the reference sound recording from the portion of the mixed audio recording to generate a new mixed audio recording; anda second subtraction component configured to compare one or more segments of the portion of the mixed audio recording with one or more corresponding segments of the new mixed audio recording and reduce at least one power level of at least one segment of the one or more corresponding segments of the new mixed audio recording based at least in part on a spectral correlation of the at least one segment of the one or more corresponding segments with at least one segment of the one or more segments of the portion of the mixed audio recording.