首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于扩展谱相减与SAP的带噪语音端点检测
引用本文:王秀丽,王树勋,林琳.基于扩展谱相减与SAP的带噪语音端点检测[J].吉林大学学报(信息科学版),2006,24(4):351-357.
作者姓名:王秀丽  王树勋  林琳
作者单位:吉林大学,通信工程学院,长春,130022
基金项目:吉林省长春市科技发展计划项目
摘    要:为提高低信噪比时带噪语音端点检测的性能,提出了一种将扩展的谱相减法与SAP(Speech AbsenceProbab ility)软门限相结合的方法。采用基于噪声补偿结构的扩展谱相减法,通过使用自适应的判决规则,在不需要进行语音激活检测的情况下有效地去除了背景噪声,克服了单麦克输入时无法在语音段对噪声进行估计的缺点。同时采用非语音段概率SAP软门限,直接对增强后的语音信号进行检测,有效提高了语音段起止端点检测的精确度和可靠性。实验结果表明,该方法比短时能量方法的计算效率高,在信噪比为-10 dB时仍能完成端点检测。

关 键 词:扩展谱相减法  噪声消除  SAP软门限  端点检测
文章编号:1671-5896(2006)04-0351-07
修稿时间:2005年8月9日

Speech Endpoint Detection Based on Expanded Spectral Subtraction and SAP
WANG Xiu-li,WANG Shu-xun,LIN Lin.Speech Endpoint Detection Based on Expanded Spectral Subtraction and SAP[J].Journal of Jilin University:Information Sci Ed,2006,24(4):351-357.
Authors:WANG Xiu-li  WANG Shu-xun  LIN Lin
Abstract:An algorithm that combines the expanded spectral subtraction with the SAP(Speech Absence Probability) soft decision is proposed to improve the capability of endpoint detection for lower R_(SNR).It uses a method of expanded spectral subtraction based on the noise compensation structure ruled by an adaptive decision,which eliminates the noise efficiently without voice activity detector,and also overcomes the typical disadvantage of one channel noise suppression algorithm,which can not estimate the noise during speech presence.At the same time,a method of end point detection based on the SAP soft decision is given,which improves the robustness and the precision of the endpoint detection.Compared to the method based on energy,the experiments show that higher efficiency and good detection capability can be obtained under the condition of R_(SNR) equal to-10 dB.
Keywords:expanded spectral subtraction  noise reduction  speech absence probability(SAP)soft decision  endpoint detection
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号