Title :
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
fDate :
4/1/1996 12:00:00 AM
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;
Journal_Title :
Signal Processing Letters, IEEE
