Subband analysis for robust speech recognition in the presence of car noise
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 417-420
- https://doi.org/10.1109/icassp.1995.479610
Abstract
A new set of speech feature representations for robust speech recognition in the presence of car noise is proposed. These parameters are based on subband analysis of the speech signal. Line spectral frequency (LSF) representation of the linear prediction (LP) analysis in subbands and cepstral coefficients derived from subband analysis (SUBCEP) are introduced, and the performances of the new feature representations are compared to mel scale cepstral coefficients (MELCEP) in the presence of car noise. Subband analysis based parameters are observed to be more robust than the commonly employed MELCEP representations.Keywords
This publication has 7 references indexed in Scilit:
- Interframe differential coding of line spectrum frequenciesIEEE Transactions on Speech and Audio Processing, 1994
- Interframe differential vector coding of line spectrum frequenciesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- On the use of line spectral frequency parameters for speech recognitionDigital Signal Processing, 1992
- A class of linear-phase regular biorthogonal waveletsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Efficient vector quantization of LPC parameters at 24 bits/framePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Analytical expressions for critical-band rate and critical bandwidth as a function of frequencyThe Journal of the Acoustical Society of America, 1980
- Line spectrum representation of linear predictor coefficients of speech signalsThe Journal of the Acoustical Society of America, 1975