Gammatone cepstral coefficients: Biologically inspired features for non-speech audio classification

Xavier Valero, Francesc Alias

Research output: Indexed journal article Articlepeer-review

202 Citations (Scopus)


In the context of non-speech audio recognition and classification for multimedia applications, it becomes essential to have a set of features able to accurately represent and discriminate among audio signals. Mel frequency cepstral coefficients (MFCC) have become a de facto standard for audio parameterization. Taking as a basis the MFCC computation scheme, the Gammatone cepstral coefficients (GTCCs) are a biologically inspired modification employing Gammatone filters with equivalent rectangular bandwidth bands. In this letter, the GTCCs, which have been previously employed in the field of speech research, are adapted for non-speech audio classification purposes. Their performance is evaluated on two audio corpora of 4 h each (general sounds and audio scenes), following two cross-validation schemes and four machine learning methods. According to the results, classification accuracies are significantly higher when employing GTCC rather than other state-of-the-art audio features. As a detailed analysis shows, with a similar computational cost, the GTCC are more effective than MFCC in representing the spectral characteristics of non-speech audio signals, especially at low frequencies.

Original languageEnglish
Article number6202347
Pages (from-to)1684-1689
Number of pages6
JournalIEEE Transactions on Multimedia
Issue number6
Publication statusPublished - 2012


  • Audio classification
  • Gammatone cepstral coefficients
  • audio scene recognition
  • environmental sound
  • feature extraction


Dive into the research topics of 'Gammatone cepstral coefficients: Biologically inspired features for non-speech audio classification'. Together they form a unique fingerprint.

Cite this