一种增强带噪语音可懂度的新算法  

Speech intelligibility enhancement by adding tunable white noise

作　　者：姚峰英[1] 张敏[1] 

机构地区：[1]中国科学院上海冶金研究所微电子学分部,上海200233

出　　处：《声学学报》2002年第6期529-530,共2页Acta Acustica

摘　　要：一般的语音增强算法在强噪声环境中只能提高信噪比,不能提高可懂度。本文提出用可调节白噪声代替信号中非语音部分的语音可懂度增强处理新算法。实验证明此方法能明显改善强噪声时的语音可懂度,能对低至-10dB的带噪语音信号进行有效的可懂度增强。Generally, speech enhancement approaches improve SNR but decrease intelligibility in very noisy environment. This paper suggests a new algorithm to improve intelligibility by replacing non-speech segments with amplitude tunable white noise. Experiments results prove that this algorithm can dramatically improve intelligibility even the input SNR is as low as -10 dB.

关 键 词：带噪语音 算法 语音增强 可懂度 语音信号处理 

分 类 号：TN912.3[电子电信—通信与信息系统]