噪声环境下语音识别方法研究

北京大学学报（自然科学版）

噪声环境下语音识别方法研究

吴淑珍,冯成林,黄新宇

北京大学电子学系，北京，100871

收稿日期:2000-04-05 出版日期:2001-05-20 发布日期:2001-05-20

Study on Noisy Speech Recognition Methods

WU Shuzhen，FENG Chenglin，HUANG Xinyu

Department of Electronics, Peking University, Beijing, 100871

Received:2000-04-05 Online:2001-05-20 Published:2001-05-20

摘要/Abstract

摘要： 研究了6种噪声背景下与说话人有关的孤立词语音识别方法。它们是：线性预测误差法，单边自相关线性预测法，语音前端声学处理法，正则相关分析的谱变换补偿方法，特征综合法和同模极点增加法。实验结果表明，这6种方法都有效地提高了噪声环境中语音识别率，其中较好的方法在强噪声环境中(信噪比为0dB)的语音识别率达到80%以上，为信噪比较低的噪声环境中自动语音识别展现了美好前景。

Abstract: There are difficulties in noisy speech recognition, especially low signal-to-noise rations are more difficult. This paper describes briefly six methods for speaker-dependent noisy speech recognition(isolated words). They are LPC prediction error method, one-side auto- correlation sequence LPC, acoustic front end processing, canonical correlation based on compensation method, combination of features method and increase of poles method. The experimental results show that all the six techniques can improve effectively noisy speech recognition, and the best noisy speech recognition rate is above 80%(when SNR=0dB).

Key words: LPC prediction error, one-side autocorrelation sequence LPC, acoustic front end processing, canonical correlation based on compensation, combination of features

中图分类号: