基于临界频带及能量熵的语音端点检测
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
语音端点检测的准确性直接关系着语音识别、合成、增强等语音领域的准确性,为了提高语音端点检测的有效性,提出了一种基于临界频带及能量熵的语音端点检测算法。算法充分利用人耳听觉特性的频率分布,将含噪语音信号进行临界频带划分,并结合各频带内信号的能量熵值在语音段和噪声段的不同分布,实现不同背景噪声下语音端点检测。实验结果表明,提出的语音端点检测算法与传统的短时能量法相比,检测正确率平均高1.6个百分点。所提方法在不同噪声的低信噪比(SNR)环境下均能实现语音端点检测。
The accuracy of the speech endpoint detection has a direct impact on the precision of speech recognition,synthesis,enhancement,etc.To improve the effectiveness of speech endpoint detection,an algorithm based on critical band and energy entropy was proposed.It took full advantage of the frequency distribution of human auditory characteristics,and divided the speech signals according to critical bands.Combined with the different distribution of energy entropy of each critical band of the signals respectively in the speech segments and noise segments,speech endpoint detection under different background noises was completed.The experimental results indicate that the average accuracy of the newly proposed algorithm is 1.6% higher than the traditional short-time energy algorithm.The proposed method can achieve the detection of speech endpoint under various noise environment of low Signal to Noise Ratio(SNR).
引文
[1]韩立华,王博,段淑凤.语音端点检测技术研究进展[J].计算机应用研究,2010,27(4):1220-1226.
    [2]王博,郭英,韩立峰.基于熵函数的语音端点检测算法研究[J].信号处理,2009,25(3):368-373.
    [3]张梅.一种基于模糊神经网络的语音端点检测方法[J].计算机工程与应用,2012,48(16):133-136.
    [4]邱文武,蒋建中,郭军利.基于小波能量熵的语音端点检测算法[J].计算机应用与软件,2011,28(2):227-229.
    [5]贾杏托,王成儒.基于多小波变换的图像去噪技术[J].计算机工程与应用,2010,46(19):204-206,237.
    [6]汤谨晖,欧阳美娟.小波变换在地震信号降噪中的应用[J].科技广场,2010(5):150-152.
    [7]王晓亚,鲁玉海.语音的端点检测处理技术[J].信号与信息处理,2010,40(2):1003-1006.
    [8]BERITELLI F,CASALE S,SERRANO S.Adaptive V/UV speechdetection based on acoustic noise estimation and classification[J].IEEE Electronics Letters,2007,43(4):249-251.
    [9]蔡萍.一种改进的基于人耳听觉掩蔽效应的语音增强算法[J].闽江学院学报,2012,33(2):70-72.
    [10]刘兵,孙超,杨益新,等.被动声纳目标临界频带频谱能量的特征提取[J].声学技术,2009,28(2):132-134.
    [11]王彪.一种改进的语音端点检测方法研究[J].电子设计工程,2012,20(4):47-50.
    [12]朱建伟,孙水发,但志平,等.基于子带二次谱熵的语音端点检测[J].微电子学与计算机,2011,28(3):77-80.
    [13]李晔,张仁智,崔慧娟,等.低信噪比下基于谱熵的语音端点检测算法[J].清华大学学报:自然科学版,2005,45(10):1397-1400.
    [14]COUVREUR L,COUVREUR C.Wavelet-based non-parametricHMM's:theory and applications[C]//ICASSP'00:Proceedings ofthe 2000 IEEE International Conference on Acoustics,Speech,and Signal Processing.Washington,DC:IEEE Computer Society,2000:604-607.
    [15]WU B F,WANG K H.Robust endpoint detection algorithm basedon the adaptive band-partitioning spectral entropy in adverse envi-ronments[J].IEEE Transactions on Speech and Audio Process-ing,2005,13(5):762-775.
    [16]LU Z M,LIU B S,SHEN L.Speech endpoint detection in strongnoisy environment based on the Hilbert-Huang transform[C]//IC-MA 2009:Proceedings of the 2009 IEEE International Conferenceon Mechatronics and Automation.Washington,DC:IEEE Com-puter Society,2009:4322-4326.

版权所有:© 2021 中国地质图书馆 中国地质调查局地学文献中心