语音增强用于抗噪声语音识别  

Speech enhancement applied to speech recognition in noisy environments

作　　者：徐义芳 张金杰 姚开盛 曹志刚[1] 王勇前[1] 

机构地区：[1]清华大学电子工程系

出　　处：《清华大学学报（自然科学版）》2001年第1期41-44,共4页Journal of Tsinghua University(Science and Technology)

摘　　要：语音识别系统通常是将在安静的环境下训练得到的参数应用于实际环境中。如果实际环境也是安静的 ,则语音识别系统可以令人满意地工作。然而 ,当实际环境中有噪声存在时 ,语音识别系统性能急剧下降。为了让语音识别系统在安静的环境和有噪声的环境中都获得令人满意的工作性能 ,研究了一个将语音增强器和语音识别器级连起来的系统。该系统中 ,语音增强作为前端处理用于提高识别器输入端信号的信噪比。通过 3种不同的增强算法用于纯净语音和3种类型带噪语音的实验结果分析比较表明 。Speech recognition systems work in practical environments using parameters train in quiet environments. The system performance is satisfactory when the environment is also quiet, but degrades quickly in noisy environments. This paper presents a noisy speech recognition system with added background noise so that the recognition system can work well both in quiet and noisy environments. Speech enhancement as the front end processing module is used to improve the Signal to Noise Ratio (SNR) of the input signal for recognition in the latter stages. Three different speech enhancement algorithms were tested with six types of noise. Experimental results show that the cascading of the speech enhancer and a Hidden Markov Model (HMM) based speech recognizer can significantly improve recognition accuracy in noisy environments without performance degradation for clean speech.

关 键 词：语音增强谱相减 语音识别 抗噪声 

分 类 号：TN912.3[电子电信—通信与信息系统]