This paper introduces a novel feature based on the raw output of the gammatone filterbank. Channel selection is used to enhance robustness over a range of signal-to-noise ratios (SNR) of additive noise. The recognition accuracy of the proposed feature is tested on a sound event database using a Hidden Markov Model (HMM) recogniser. A comparison with a series of similar features and the conventional Mel-Frequency Cepstral Coefficients (MFCC) shows that the proposed feature offers significant improvement in low SNR conditions.
Bibliographic reference. Leng, Yi Ren / Tran, Huy Dat / Kitaoka, Norihide / Li, Haizhou (2010): "Selective gammatone filterbank feature for robust sound event recognition", In INTERSPEECH-2010, 2246-2249.