背景噪声下的语音识别技术研究

Research on Noisy Speech Recognition Technology

研究了3种背景噪声下与说话人有关的孤立词语音识别方法。即语音前端声学处理法、正则相关分析的谱变换补偿方法和同模极点增加法。实验结果表明,这3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0 dB)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。

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