Browse Prior Art Database

STEREO AUDIO FINGERPRINTING AND MATCHING

IP.com Disclosure Number: IPCOM000237526D
Publication Date: 2014-Jun-19
Document File: 17 page(s) / 1M

Publishing Venue

The IP.com Prior Art Database

Abstract

Systems and techniques for stereo audio fingerprinting and/or matching are presented. A fingerprint component generates a first audio fingerprint for a first audio channel associated with media content, a second audio fingerprint for a second audio channel associated with the media content, and a third audio fingerprint for a merged audio channel generated based on the first audio channel and the second audio channel. A matching component performs audio fingerprint matching based on the third audio fingerprint and at least one of the first audio fingerprint or the second audio fingerprint.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 3% of the total text.

Page 01 of 17

STEREO AUDIO FINGERPRINTING AND MATCHING

This disclosure relates generally to fingerprint matching, and more specifically, to stereo audio fingerprinting and matching.

BACKGROUND

     Audio matching provides for identification of a recorded audio sample by comparing an audio sample to a set of reference samples. One example of a recorded audio sample can be an audio track of a video. To make the comparison, an audio sample can be transformed into an audio fingerprint. As such, the audio fingerprint for the audio sample can be compared to audio fingerprints of reference samples to determine the identity of the audio sample.

     Typical audio fingerprinting schemes work with mono input (e.g., single channel input). However, in reality, most audio files are not mono input (e.g., single channel input). Some existing audio fingerprinting schemes assume a mono input and other existing audio fingerprinting schemes merge audio channels before computing a fingerprint. However, merging audio channels before computing a fingerprint can result in a loss of information. For example, if one of the audio channels is distorted or noisy, both audio channels can become distorted when merged.

SUMMARY

     The following presents a simplified summary of the specification in order to provide a basic understanding of some aspects of the specification. This summary is not an extensive overview of the specification. Its sole purpose is to present some concepts of the specification in a simplified form as a prelude to the more detailed description that is presented later.

     In accordance with an implementation, a system includes a fingerprint component and a matching component. The fingerprint component generates a first audio fingerprint for a first audio channel associated with media content, a second audio fingerprint for a second audio channel associated with the media content, and a third audio fingerprint for a merged audio channel generated based on the first audio channel and the second audio channel. The matching component performs audio fingerprint matching based on the third audio fingerprint and at least one of the first audio fingerprint or the second audio fingerprint.

     Additionally, a non-limiting implementation provides for generating a first audio fingerprint for a first audio channel associated with media content, generating a second audio fingerprint for a second audio channel associated with the media content, generating a third audio fingerprint for a merged audio channel generated based on the first audio channel and the second audio channel, and performing audio fingerprint matching based on the third audio fingerprint and at least one of the first audio fingerprint or the second audio fingerprint.

     In accordance with another implementation, a non-transitory computer readable storage medium comprising computer-executable instructions, that in response to execution, cause a computing system to perform operations, comprising: generating a first audio...