Presentation | 1998/12/10 Speaker normalized spectral subband parameters for noise robust speech recognition Satoru Tsuge, Toshiaki Fukada, Haraldr Singer, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper proposes speaker normalized spectral subband centroids(SSCs)as supplementary features in noise environment speech recognition. SSCs are computed as frequency centroids for each subband from the power spectrum of the speech signal. This feature can be obtained reliably even under noisy conditions because SSC are mainly computed from spectral peaks sucn as fromants whose positions are almost unchanged in a noisy environment. Since the conventional SSCs depend on formant frequencies of a speaker, the distributions of SSCs computed from large amounts of speakers will be highly overlapped between different phones. Therefore, we introduce a speaker normalization technique into SSC computation to reduce the speaker variability. Experimental results on spontaneous speech recognition show that the speaker normalized SSCs are more useful as supplementary features for improving the recognition performance that the conventional SSCs. We observed a significant improvement in error rate by 20.3% and 14.3% at SNR=15dB by adding speaker normalied SSCs to the conventional features nad by incorporating a speaker normalized technique into the conventional SSCs, respectively. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Spectral subband centroids / Noise environment / Speaker normalization / Speech recognition |
Paper # | NLC98-40,SP98-104 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 1998/12/10(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Natural Language Understanding and Models of Communication (NLC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Speaker normalized spectral subband parameters for noise robust speech recognition |
Sub Title (in English) | |
Keyword(1) | Spectral subband centroids |
Keyword(2) | Noise environment |
Keyword(3) | Speaker normalization |
Keyword(4) | Speech recognition |
1st Author's Name | Satoru Tsuge |
1st Author's Affiliation | ATR Interpreting Telecommunications Research Laboratories:Tokushima University() |
2nd Author's Name | Toshiaki Fukada |
2nd Author's Affiliation | ATR Interpreting Telecommunications Research Laboratories |
3rd Author's Name | Haraldr Singer |
3rd Author's Affiliation | ATR Interpreting Telecommunications Research Laboratories |
Date | 1998/12/10 |
Paper # | NLC98-40,SP98-104 |
Volume (vol) | vol.98 |
Number (no) | 460 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |