Abstract | ||
---|---|---|
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. Since the conventional SSCs depend on the formant frequencies of a speaker, 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 than the conventional SSCs. |
Year | DOI | Venue |
---|---|---|
1999 | 10.1109/ICASSP.1999.758118 | The Journal of The Acoustical Society of Japan (e) |
Keywords | DocType | ISSN |
supplementary feature,recognition performance,speaker variability,conventional sscs,speech signal,speaker normalization technique,noise robust speech recognition,spontaneous speech recognition show,speaker normalized sscs,noise environment speech recognition,spectral subband centroid,spectral subband parameter,testing,feature extraction,signal to noise ratio,dynamic range,power spectrum,databases,noise shaping,parameter estimation,noise,formant frequencies,speech recognition | Conference | 1520-6149 |
ISBN | Citations | PageRank |
0-7803-5041-3 | 5 | 0.77 |
References | Authors | |
6 | 3 |