Analysis of LPC/DFT features for an HMM-based alphadigit recognizer

Author

Mashao, Daniel J. ; Gotoh, Yoshihiko ; Silverman, Harvey F.

Author_Institution

Div. of Eng., Brown Univ., Providence, RI, USA

Volume

3

Issue

4

fYear

1996

fDate

4/1/1996 12:00:00 AM

Firstpage

103

Lastpage

106

Abstract

The search for better and more robust performance of speech recognition systems is ongoing. Much of the improvement is likely to come from better acoustic feature analysis. The results from a significant experiment are reported; these show how a warped-DFT analysis outperforms an LPC-cepstral analysis in a significant way, supporting results by other researchers for different recognition tasks. An analysis of nasal-letter performance is used to show the development of the warped-DFT feature analysis.

Keywords

acoustic signal processing; discrete Fourier transforms; feature extraction; hidden Markov models; linear predictive coding; speech coding; speech processing; speech recognition; HMM based alphadigit recognizer; LPC-cepstral analysis; LPC/DFT features analysis; acoustic feature analysis; experiment; nasal-letter performance; recognition tasks; speech recognition systems; warped-DFT analysis; warped-DFT feature analysis; Artificial neural networks; Cepstral analysis; Hidden Markov models; Linear predictive coding; Performance analysis; Robustness; Speech recognition; Testing; Time frequency analysis; Vocabulary;

fLanguage

English

Journal_Title

Signal Processing Letters, IEEE

Publisher

ieee

ISSN

1070-9908

Type

jour

DOI

10.1109/97.489061

Filename

489061