指数函数规整群时延的VAD特征研究

吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (增刊1): 435-439.

指数函数规整群时延的VAD特征研究

王金芳, 虢明

吉林大学通信工程学院, 长春 130012

收稿日期:2012-06-07 发布日期:2013-06-01
作者简介:王金芳(1969- ),男,副教授.研究方向:语音信号处理.Email:jinfangw@163.com

Research on VAD feature of exponent function warping group delay function

WANG Jin-fang, GUO Ming

College of Communications Engineering, Jilin University, Changchun 130012, China

Received:2012-06-07 Published:2013-06-01

摘要/Abstract

摘要：

虽然群时延函数的噪声鲁棒性已得到证明,但谐振引起的尖峰效应严重影响进一步的实际应用。为了保证对原声学空间的表征效力,在减少特征提取过程信息丢失的前提下,以降低群时延谱的动态范围为目标,提出指数函数规整群时延的特征参数。语音活动检测测试实验表明,其噪声鲁棒性和检测准确度相对于现有群时延函数特征有明显提高。

关键词: 语音信号处理, 语音活动检测, 指数函数规整, 群时延函数

Abstract:

Although the robustness to noise of group delay function (GDF) was proved,the spiky effects caused by the resonance seriously undermined its further application.The ability to represent the original acoustic space was by no means guaranteed for the current improvement solutions.On the premise reducing the information loss in the process of feature extraction and aiming at decreasing its dynamic range,the feature of exponent function warping group delay function was produced.The test experiments of voice activity detection indicate that the robustness and detection accuracy is raised remarkably compared to the present GDF versions.

Key words: speech signal processing, voice activity detection, exponent function warping, group delay function

中图分类号:

TN912.3

王金芳, 虢明. 指数函数规整群时延的VAD特征研究[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 435-439.

WANG Jin-fang, GUO Ming. Research on VAD feature of exponent function warping group delay function[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 435-439.

参考文献

[1] Dong E,Liu G,Zhou Y,et al.Voice activity detection based on short-time energy and noise spectrum adaptation[C]//In 2002 6th International Conference on Signal Processing(ICSP'02),Beijing,China,2002:464-467.

[2] Sangwan A,Chiranth M C,Jamadagni H S,et al.VAD techniques for real-time speech transmission on the Internet[C]//In 5th IEEE International Conference on High Speed Networks and Multimedia Communications,Jeju Island,Korea,2002:46-50.

[3] Nemer E,Goubran R,Mahmoud S.Robust voice activity detection using higher-order statistics in the LPC residual domain[J].IEEE Transactions on Speech and Audio Processing,2001,9:217-231.

[4] Alsteris L D,Paliwal K K.Short-time phase spectrum in speech processing:a review and some experimental results[J].Digital Signal Processing,2007,17:578-616.

[5] Murthy H A,Gadde V.The modified group delay function and its application to phoneme recognition[C]//In 2003 IEEE International Conference on Acoustics,Speech,and Signal Processing (ICASSP'03),Hong Kong,China,2003:68-71.

[6] Murthy H A,Madhu Murthy K V,Yegnanarayana B.Formant extraction from phase using weighted group delay function[J].Electronics Letters,1989,25:1609-1611.

[7] Yegnanarayana B,Murthy H A.Significance of group delay functions in spectrum estimation[J].IEEE Transactions on Signal Processing,1992,40:2281-2289.

[8] Murthy H A,Yegnanarayana B.Group delay functions and its applications in speech technology[J].Springer,2011,36:745-782.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed