| 基于听觉场景分析的近讲语音增强算法 |
| |
| 引用本文： | 胡奎,梁维谦.基于听觉场景分析的近讲语音增强算法[J].清华大学学报(自然科学版),2011(9). |
| |
| 作者姓名： | 胡奎 梁维谦 |
| |
| 作者单位： | 清华大学微电子与纳电子学系;清华大学电子工程系; |
| |
| 基金项目： | 国家“八六三”高技术项目(2008AA010700) |
| |
| 摘 要： | 针对近讲场景,提出一种双麦克近讲语音增强算法。该算法基于耳间延时差(ITD)、耳间强度差(IID)特征来区分目标语音,利用声学掩蔽效应,实现目标语音对背景噪声的分离降噪。与传统的单麦克增强方法相比,该算法可消除多种类型噪声且对语音造成的损伤较小。实验表明:该算法能将8～33dB的白噪声、音乐噪声、广播噪声3种噪声类型的带噪语音的信噪比提高到36dB以上,同时保持较高的目标语音可懂度。对于冲击噪声的带噪语音也具有较好的降噪效果。
|
| 关 键 词： | 语音增强 听觉场景分析 耳间延时差 耳间能量差 声学掩蔽 |
Close-talk speech enhancement algorithm based on CASA |
| |
| HU Kui ,LIANG Weiqian.Close-talk speech enhancement algorithm based on CASA[J].Journal of Tsinghua University(Science and Technology),2011(9). |
| |
| Authors: | HU Kui LIANG Weiqian |
| |
| Institution: | HU Kui 1,LIANG Weiqian 2(1.Institute of Microelectronics,Tsinghua University,Beijing 100084,China,2.Department of Electronic Engineering,China) |
| |
| Abstract: | A two-microphone speech enhancement algorithm was developed for close-talk applications.The algorithm segregates the target speech from the noisy speech using cues such as the interaural time difference(ITD),the interaural intensity difference(IID) and the masking effect.This algorithm suppresses more kinds of noise with less speech distortion than single-microphone speech enhancement methods.Tests show that the algorithm increases the SNR of 3 kinds of noisy signals from 8~33 dB to 36 dB.The enhanced speec... |
| |
| Keywords: | speech enhancement auditory scene analysis interaural time differences(ITD) interaural intensity differences(IID) masking effect |
| 本文献已被 CNKI 等数据库收录！ |
