Temporal decomposition: a framework for enhanced speech recognition

Author

Niranjan, Mahesan ; Fallside, Frank

Author_Institution

Dept. of Eng., Cambridge Univ., UK

fYear

1989

fDate

23-26 May 1989

Firstpage

655

Abstract

Short term spectral analysis of source-filter modeling gives a parameterized description of the acoustic signal in terms of a sequence of vectors. These parameter vectors change slowly with time corresponding to a slowly moving vocal tract. The authors consider a model (temporal decomposition) that approximates the time variation by a set of target vectors and interpolation functions that overlap in time. They present a geometric interpretation of the approach, describe an algorithm for decomposing a given utterance into parameters of such a model, and discuss how such modeling can be used in speech recognition systems

Keywords

acoustic signal processing; filtering and prediction theory; spectral analysis; speech analysis and processing; speech recognition; acoustic signal; algorithm; geometric interpretation; interpolation functions; parameter vectors; short term spectral analysis; slowly moving vocal tract; source-filter modeling; speech recognition; target vectors; temporal decomposition; utterance; Acoustical engineering; Hidden Markov models; Interpolation; Length measurement; Power system modeling; Shape; Signal generators; Solid modeling; Spectral analysis; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on

Conference_Location

Glasgow

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1989.266512

Filename

266512