Histogram equalization for noise-robust speech recognition using discrete-mixture HMMs

Acoustical Science and Technology

Masaharu Katoh¹  Masaki Kohda¹  Tetsuo Kosaka¹ 

[1] Graduate School of Science and Engineering, Yamagata University

关键词: Speech recognition;    Noise robustness;    Hidden Markov model;    Discrete HMMs;    Histogram equalization;   

DOI  :  10.1250/ast.29.66

学科分类：声学和超声波

来源: Acoustical Society of Japan

【 摘 要 】

References(10)Cited-By(1)In this paper, we introduce a new method of robust speech recognition under noisy conditions based on discrete-mixture hidden Markov models (DMHMMs). DMHMMs were originally proposed to reduce calculation costs in the decoding process. Recently, we have applied DMHMMs to noisy speech recognition, and found that they were effective for modeling noisy speech. Towards the further improvement of noise-robust speech recognition, we propose a novel normalization method for DMHMMs based on histogram equalization (HEQ). The HEQ method can compensate the nonlinear effects of additive noise. It is generally used for the feature space normalization of continuous-mixture HMM (CMHMM) systems. In this paper, we propose both model space and feature space normalization of DMHMMs by using HEQ. In the model space normalization, codebooks of DMHMMs are modified by the transform function derived from the HEQ method. The proposed method was compared using both conventional CMHMMs and DMHMMs. The results showed that the model space normalization of DMHMMs by multiple transform functions was effective for noise-robust speech recognition.

【 授权许可】

Unknown