欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
文中针对带噪的耳语音提出了一种LMS自适应滤波的耳语音增强算法。首先采用谱减法得到一个增强耳语音信号，取得较好的谱包络后对增强信号进行LMS自适应滤波，消除由谱减法产生的音乐噪声。结果表明，采集到的耳语音信号的质量得到明显提高，即使在低信噪比的情况下，信噪比也能提高20dB左右。
英文摘要：
This paper introduces a method based on the combination of spectral subtraction and LMS adaptive filtering in the enhancement .of Chinese whispered speech. First, an enhanced whispered speech by spectral subtraction is obtained, then the LMS adaptive filtering is applied to the enhanced signal to decrease the musical noise. The result shows that the quality of whispered speech is obviously enhanced and the SNR output can be improved by 20 dB even if the SNR input is low. The algorithm can result in SNR improvement.
同期刊论文项目
同项目期刊论文
期刊信息
位置：