Cover song identification with direct chroma feature extraction from AAC files

Tai Ming Chang, En Ting Chen, Chia Bin Hsieh, Pao Chi Chang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

This paper proposes a low-complexity and effective feature extraction method derived directly from AAC files. Unlike traditional methods that must decode audio files and then compute fast Fourier transform coefficients, the proposed system directly maps the modified discrete cosine transform coefficients into a 12-dimenional chroma feature without fully decoding it. To accelerate the matching time, segmentation is applied to reduce the time dimension in the feature space. In addition, the dynamic programming technique is used to match songs to various tempos. The experimental results show that the proposed system achieves a 62% accuracy rate, which is an improvement over the traditional FFT-based system, and reduces the computational complexity by approximately 35%.

Original languageEnglish
Title of host publication2013 IEEE 2nd Global Conference on Consumer Electronics, GCCE 2013
Pages55-56
Number of pages2
DOIs
StatePublished - 2013
Event2013 IEEE 2nd Global Conference on Consumer Electronics, GCCE 2013 - Tokyo, Japan
Duration: 1 Oct 20134 Oct 2013

Publication series

Name2013 IEEE 2nd Global Conference on Consumer Electronics, GCCE 2013

Conference

Conference2013 IEEE 2nd Global Conference on Consumer Electronics, GCCE 2013
Country/TerritoryJapan
CityTokyo
Period1/10/134/10/13

Keywords

  • AAC
  • chroma feature
  • cover song
  • MDCT
  • music information retrieval

Fingerprint

Dive into the research topics of 'Cover song identification with direct chroma feature extraction from AAC files'. Together they form a unique fingerprint.

Cite this