Recognition of Noisy Speech Using Dynamic Spectral Subband Centroids
Authors:
- K.K. PaliwalKPK.K. Paliwal
- 30 January 2004
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 11 (2) , 258-261
Abstract
Despite their widespread popularity as front-end parameters for speech recognition, the cepstral coefficients derived from either linear prediction analysis or a filter-bank are found to be sensitive to additive noise. In this letter, we discuss the use of spectral subband centroids for robust speech recognition. We show that centroids, if properly selected, can achieve recognition performance comparable to that of the mel-frequency cepstral coefficients (MFCCs) in clean speech, while delivering better performance than MFCC in noisy environments. A procedure is proposed to construct the dynamic centroid feature vector that essentially embodies the transitional spectral information. We discuss some properties of the proposed dynamic features.Keywords
This publication has 11 references indexed in Scilit:
- On the use of instantaneous and transitional spectral information in speaker recognition2005
- Evaluating the Aurora connected digit recognition task -- a bell labs approach2001
- Time-frequency distributions for automatic speech recognitionIEEE Transactions on Speech and Audio Processing, 2001
- On the relevance of language in speaker recognition1999
- Speaker normalized spectral subband parameters for noise robust speech recognition1999
- Spectral subband centroid features for speech recognition1998
- Time-frequency analysis and auditory modeling for automatic recognition of speechProceedings of the IEEE, 1996
- Spectral Dynamics for Speech Recognition Under Adverse Conditions1996
- Auditory models and human performance in tasks related to speech coding and speech recognitionIEEE Transactions on Speech and Audio Processing, 1994
- Cepstral analysis technique for automatic speaker verificationIEEE Transactions on Acoustics, Speech, and Signal Processing, 1981