Subband analysis for robust speech recognition in the presence of car noise

Author

Erzin, Engin ; çetin, A. Enis ; Yardimci, Yasemin

Author_Institution

Bilkent Univ., Ankara, Turkey

Volume

1

fYear

1995

fDate

9-12 May 1995

Firstpage

417

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

acoustic noise; cepstral analysis; feature extraction; prediction theory; speech processing; speech recognition; MELCEP; SUBCEP; car noise; cepstral coefficients; line spectral frequency representation; linear prediction analysis; mel scale cepstral coefficients; robust speech recognition; speech feature representations; subband analysis; Cepstral analysis; Filters; Frequency; Hidden Markov models; Linear predictive coding; Noise robustness; Performance analysis; Signal analysis; Speech analysis; Speech recognition; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on

Conference_Location

Detroit, MI

ISSN

1520-6149

Print_ISBN

0-7803-2431-5

Type

conf

DOI

10.1109/ICASSP.1995.479610

Filename

479610