首页> 外文期刊>Computer speech and language >Improved voice activity detection algorithm using wavelet and support vector machine
【24h】

Improved voice activity detection algorithm using wavelet and support vector machine

机译:改进的基于小波和支持向量机的语音活动检测算法

获取原文
获取原文并翻译 | 示例

摘要

This paper proposes an improved voice activity detection (VAD) algorithm using wavelet and support vector machine (SVM) for European Telecommunication Standards Institution (ETSI) adaptive multi-rate (AMR) narrow-band (NB) and wide-band (WB) speech codecs. First, based on the wavelet transform, the original IIR filter bank and pitch/tone detector are implemented, respectively, via the wavelet filter bank and the wavelet-based pitch/tone detection algorithm. The wavelet filter bank can divide input speech signal into several frequency bands so that the signal power level at each sub-band can be calculated. In addition, the background noise level can be estimated in each sub-band by using the wavelet de-noising method. The wavelet filter bank is also derived to detect correlated complex signals like music. Then the proposed algorithm can apply SVM to train an optimized non-linear VAD decision rule involving the sub-band power, noise level, pitch period, tone flag, and complex signals warning flag of input speech signals. By the use of the trained SVM, the proposed VAD algorithm can produce more accurate detection results. Various experimental results carried out from the Aurora speech database with different noise conditions show that the proposed algorithm gives considerable VAD performances superior to the AMR-NB VAD Options 1 and 2, and AMR-WB VAD.
机译:本文针对欧洲电信标准协会(ETSI)自适应多速率(AMR)窄带(NB)和宽带(WB)语音,提出了一种使用小波和支持向量机(SVM)的改进的语音活动检测(VAD)算法编解码器。首先,基于小波变换,分别通过小波滤波器组和基于小波的基音/音调检测算法分别实现了原始IIR滤波器组和基音/音调检测器。小波滤波器组可以将输入的语音信号划分为几个频带,以便可以计算每个子频带的信号功率电平。另外,可以通过使用小波消噪方法来估计每个子带中的背景噪声水平。小波滤波器组也被导出以检测相关的复杂信号,例如音乐。然后,该算法可以应用支持向量机来训练优化的非线性VAD决策规则,该规则涉及输入语音信号的子带功率,噪声电平,基音周期,音调标志和复信号警告标志。通过使用训练有素的SVM,提出的VAD算法可以产生更准确的检测结果。从Aurora语音数据库在不同噪声条件下进行的各种实验结果表明,所提出的算法可提供比AMR-NB VAD选项1和2和AMR-WB VAD更好的VAD性能。

著录项

  • 来源
    《Computer speech and language》 |2010年第3期|p.531-543|共13页
  • 作者单位

    Department of Computer Science and Information Engineering, Shu-Te University, Kaohsiung County, 824, Taiwan, ROC;

    University of Sao Paulo (USP), Institute of Physics at Sao Carlos (IFSC), Department of Physics and Informatics (FFI), Avenida Trabalhador SaoCarlense 400, 13566-590 Sao Carlos, SP, Brazil;

    rnDepartment of Information Engineering, I-Shou University, Kaohsiung County, 840, Taiwan, ROC;

    Department of Applied Mathematics, I-Shou University, Kaohsiung County, 840, Taiwan, ROC;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    voice activity detection (VAD); AMR-NB; AMR-WB; wavelet transform; support vector machine (SVM);

    机译:语音活动检测(VAD);AMR-NB;AMR-WB;小波变换支持向量机(SVM);

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号