A study of LSF representation for speaker-dependent and speaker-independent HMM-based speech recognition systems

Author

Paliwal, K.

Author_Institution

AT&T Bell Lab., Murray Hill, NJ, USA

fYear

1990

fDate

3-6 Apr 1990

Firstpage

801

Abstract

The line spectral-pair frequency (LSF) representation is used as the parametric representation for speech recognition. Its performance is compared with that of the cepstral coefficient (CC) representation for the speaker-dependent and speaker-independent hidden Markov model (HMM)-based isolated work recognition systems. It is shown that the CC and the LSF representations result in comparable recognition performances for the full covariance matrix case. For the diagonal covariance matrix case, the LSF representation provides significantly better recognition performance than the CC representation

Keywords

Markov processes; speech recognition; cepstral coefficient; diagonal covariance matrix; isolated work recognition systems; line spectral-pair frequency; parametric representation; speaker-dependent HMM model; speaker-independent hidden Markov model; vowel recognition; Acoustics; Cepstral analysis; Covariance matrix; Filters; Frequency; Hidden Markov models; Polynomials; Speech analysis; Speech recognition; Speech synthesis;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115935

Filename

115935