DMCA
Recursive Estimation of Time-Varying Environments for Robust Speech Recognition (2001)
| Venue: | in ICASSP, 2001 |
| Citations: | 2 - 0 self |
BibTeX
@INPROCEEDINGS{Zhao01recursiveestimation,
author = {Yunxin Zhao and Shaojun Wang and Kuan-chieh Yen},
title = {Recursive Estimation of Time-Varying Environments for Robust Speech Recognition},
booktitle = {in ICASSP, 2001},
year = {2001},
pages = {225--228}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
An EM-type of recursive estimation algorithm is formulated in the DFT domain for joint estimation of time-varying parameters of distortion channel and additive noise from online degraded speech. Speech features are estimated from the posterior estimates of short-time speech power spectra in an on-the-fly fashion. Experiments were performed on speaker-independent continuous speech recognition using features of perceptually based linear prediction cepstral coefficients, log energy, and temporal regression coefficients. Speech data were taken from the TIMIT database and were degraded by simulated time-varying channel and noise. Experimental results showed significant improvement in recognition word accuracy due to the proposed recursive estimation as compared with the results from direct recognition using a baseline system and from performing speech feature estimation using a batch EM algorithm. 1.
Keyphrases
recursive estimation robust speech recognition time-varying environment log energy direct recognition speech feature short-time speech power spectrum simulated time-varying channel temporal regression coefficient distortion channel significant improvement baseline system speech data linear prediction cepstral coefficient recursive estimation algorithm speech feature estimation batch em algorithm on-the-fly fashion dft domain additive noise posterior estimate timit database recognition word accuracy time-varying parameter speaker-independent continuous speech recognition experimental result joint estimation
