Conventional features for Automatic Speech Recognition and Sound Event Recognition such as Mel-Frequency Cepstral Coefficients (MFCCs) have been shown to perform poorly in noisy conditions. We introduce an auditory feature based on the gammatone filterbank, the Selective Gammatone Envelope Feature (SGEF), for Robust Sound Event Recognition where channel selection and the filterbank envelope is used to reduce the effect of noise for specific noise environments. In the experiments with Hidden Markov Model (HMM) recognizers, we shall show that our feature outperforms MFCCs significantly in four different noisy environments at various signal-to-noise ratios.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Yi Ren LENG, Huy Dat TRAN, Norihide KITAOKA, Haizhou LI, "Selective Gammatone Envelope Feature for Robust Sound Event Recognition" in IEICE TRANSACTIONS on Information,
vol. E95-D, no. 5, pp. 1229-1237, May 2012, doi: 10.1587/transinf.E95.D.1229.
Abstract: Conventional features for Automatic Speech Recognition and Sound Event Recognition such as Mel-Frequency Cepstral Coefficients (MFCCs) have been shown to perform poorly in noisy conditions. We introduce an auditory feature based on the gammatone filterbank, the Selective Gammatone Envelope Feature (SGEF), for Robust Sound Event Recognition where channel selection and the filterbank envelope is used to reduce the effect of noise for specific noise environments. In the experiments with Hidden Markov Model (HMM) recognizers, we shall show that our feature outperforms MFCCs significantly in four different noisy environments at various signal-to-noise ratios.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.1229/_p
Copy
@ARTICLE{e95-d_5_1229,
author={Yi Ren LENG, Huy Dat TRAN, Norihide KITAOKA, Haizhou LI, },
journal={IEICE TRANSACTIONS on Information},
title={Selective Gammatone Envelope Feature for Robust Sound Event Recognition},
year={2012},
volume={E95-D},
number={5},
pages={1229-1237},
abstract={Conventional features for Automatic Speech Recognition and Sound Event Recognition such as Mel-Frequency Cepstral Coefficients (MFCCs) have been shown to perform poorly in noisy conditions. We introduce an auditory feature based on the gammatone filterbank, the Selective Gammatone Envelope Feature (SGEF), for Robust Sound Event Recognition where channel selection and the filterbank envelope is used to reduce the effect of noise for specific noise environments. In the experiments with Hidden Markov Model (HMM) recognizers, we shall show that our feature outperforms MFCCs significantly in four different noisy environments at various signal-to-noise ratios.},
keywords={},
doi={10.1587/transinf.E95.D.1229},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Selective Gammatone Envelope Feature for Robust Sound Event Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1229
EP - 1237
AU - Yi Ren LENG
AU - Huy Dat TRAN
AU - Norihide KITAOKA
AU - Haizhou LI
PY - 2012
DO - 10.1587/transinf.E95.D.1229
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2012
AB - Conventional features for Automatic Speech Recognition and Sound Event Recognition such as Mel-Frequency Cepstral Coefficients (MFCCs) have been shown to perform poorly in noisy conditions. We introduce an auditory feature based on the gammatone filterbank, the Selective Gammatone Envelope Feature (SGEF), for Robust Sound Event Recognition where channel selection and the filterbank envelope is used to reduce the effect of noise for specific noise environments. In the experiments with Hidden Markov Model (HMM) recognizers, we shall show that our feature outperforms MFCCs significantly in four different noisy environments at various signal-to-noise ratios.
ER -