Feature Extraction with Combination of HMT-Based Denoising and Weighted Filter Bank Analysis for Robust Speech Recognition

Sungyun JUNG  Jongmok SON  Keunsung BAE  

IEICE TRANSACTIONS on Information and Systems   Vol.E88-D   No.3   pp.435-438
Publication Date: 2005/03/01
Online ISSN: 
DOI: 10.1093/ietisy/e88-d.3.435
Print ISSN: 0916-8532
Type of Manuscript: Special Section LETTER (Special Section on Corpus-Based Speech Technologies)
Hidden Markov Tree model,  robust speech recognition,  residual noise,  feature extraction,  

Full Text: PDF>>
Buy this Article

In this paper, we propose a new feature extraction method that combines both HMT-based denoising and weighted filter bank analysis for robust speech recognition. The proposed method is made up of two stages in cascade. The first stage is denoising process based on the wavelet domain Hidden Markov Tree model, and the second one is the filter bank analysis with weighting coefficients obtained from the residual noise in the first stage. To evaluate performance of the proposed method, recognition experiments were carried out for additive white Gaussian and pink noise with signal-to-noise ratio from 25 dB to 0 dB. Experiment results demonstrate the superiority of the proposed method to the conventional ones.