An analysis-synthesis hidden Markov model of speech

Author

Farges, Eric P. ; Clements, Mark A.

Author_Institution

Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA

fYear

1988

fDate

11-14 Apr 1988

Firstpage

323

Abstract

Continuous speech from one male American speaker is described by a single, large, hidden Markov model. The problems of model parameter estimation, speech-state decoding, and speech-observation decoding are presented under a unified conceptual framework built around a maximum-likelihood approach. The model has 64 states and 1024 observations, and is assumed to be fully connected. This model possesses not only speech analysis but also speech synthesis capabilities. Very-low-bit-rate speech coding is made possible by the fact that very little information is needed to encode speech state sequences. Intelligible speech was produced at 1.68 bits/frame, whereas a 2 bits/frame pitched-excited LPC vector quantizer did not produce intelligible speech

Keywords

Markov processes; decoding; encoding; parameter estimation; speech analysis and processing; speech synthesis; continuous speech; hidden Markov model; intelligible speech; maximum-likelihood approach; parameter estimation; speech analysis; speech coding; speech state sequences; speech synthesis; speech-observation decoding; speech-state decoding; Bit rate; Databases; Hidden Markov models; Linear predictive coding; Maximum likelihood decoding; Maximum likelihood estimation; Parameter estimation; Speech analysis; Speech coding; Speech synthesis;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on

Conference_Location

New York, NY

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1988.196581

Filename

196581