Automatic Adjustment of Subband Likelihood Recombination Weights for Improving Noise-Robustness of a Multi-SNR Multi-Band Speaker Identification System

Kenichi YOSHIDA  Kazuyuki TAKAGI  Kazuhiko OZEKI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E87-D   No.11   pp.2453-2459
Publication Date: 2004/11/01
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Speech and Hearing
Keyword: 
multi-SNR multi-band method,  noise-robustness,  speaker identification,  subband recombination weight,  spectral subtraction,  

Full Text: PDF>>
Buy this Article




Summary: 
This paper is concerned with improving noise-robustness of a multi-SNR multi-band speaker identification system by introducing automatic adjustment of subband likelihood recombination weights. The adjustment is performed on the basis of subband power calculated from the noise observed just before the speech starts in the input signal. To evaluate the noise-robustness of this system, text-independent speaker identification experiments were conducted on speech data corrupted with noises recorded in five environments: "bus," "car," "office," "lobby," and "restaurant". It was found that the present method reduces the identification error by 15.9% compared with the multi-SNR multi-band method with equal recombination weights at 0 dB SNR. The performance of the present method was compared with a clean fullband method in which a speaker model training is performed on clean speech data, and spectral subtraction is applied to the input signal in the speaker identification stage. When the clean fullband method without spectral subtraction is taken as a baseline, the multi-SNR multi-band method with automatic adjustment of recombination weights attained 56.8% error reduction on average, while the average error reduction rate of the clean fullband method with spectral subtraction was 11.4% at 0 dB SNR.