期刊文献+

基于在线单类支持向量机的自适应语音活动检测

Adaptive voice activity detection based on on-line one-class SVM
下载PDF
导出
摘要 针对非平稳噪声环境下的语音活动检测问题,提出了基于在线单类SVM的自适应语音活动检测算法。该算法采用单类SVM对多种特征信息进行在线学习与综合,为非平稳背景噪声建模,并采用双层决策机制,能有效提高语音活动检测的稳健性。在语音识别系统中的实验结果表明,算法在多种噪声环境和信噪比条件下有效,并明显提高了在非平稳噪声环境下的识别率。 To improve the robustness of voice activity detection for non-stationary noises, a new algorithm based on on-line one-class SVM is proposed. This algorithm uses one-class SVM to model the noisy environment by on-line learning and integrating on multiple features. And a two-level decision mechanism which can effectively improve the robustness of speech detection is utilized in construction of the algorithm. Experimental results of speech recognition system indicate that this proposed algorithm is efficient in various noisy environments at any SNR. And the recognition performance in non-stationary noise can also be increased obviously.
作者 蔡铁
出处 《深圳信息职业技术学院学报》 2008年第2期17-22,共6页 Journal of Shenzhen Institute of Information Technology
基金 深圳市科技计划项目[SZKJ0708]
关键词 语音活动检测 单类支持向量机 在线学习 voice activity detection one-class SVM on-line learning
  • 相关文献

参考文献2

二级参考文献21

  • 1[1]BRADY P T. A technique for investigating on-off patterns of speech[J]. Bell Syst Tech J, 1965, 44:1-22. 被引量:1
  • 2[2]GERSHO A, PAKSOY E. An overview of variable rate speech coding for cellular networks[A]. IEEE Conf Selected on Topics Wireless Commun[C]. Vancouver, 1992.172-175. 被引量:1
  • 3[3]BULLINGTON K, FRASER J M. Engineering aspects of TASI[J]. Bell Syst Tech J, 1959, 353-364. 被引量:1
  • 4[4]TANRIKULU O, BAYKAL B, CONSTANTINIDES A G, et al. Residual echo signal in critically sampled subband acoustic echo cancellers based on IIR and FIR filter banks[J]. IEEE Trans on Signal Proccessing, 1997,45(4):901-912. 被引量:1
  • 5[5]RABINER L R, SAMBUR M R. Voiced-unvoiced-silence detection using the Itakura LPC distance measure[A]. IEEE Int Conf Acoust, Speech and Signal Processing[C]. Hartford, CT,USA, 1977. 323-326. 被引量:1
  • 6[6]YONMA N B, MCINNES F, JACK M. Robust speech pulse-detection using adaptive noise modeling[J]. Electron Lett, 1996, 32(15):1350-1352. 被引量:1
  • 7[7]TUCKER R. Voice activity detection using a periodicity measure[J]. Proc Inst Elect Eng, 1992, 139:377-380. 被引量:1
  • 8[8]JONGSEO S, NAM S K, WONYONG S. A statistical model_based voice activity detection[J]. IEEE Signal Processing Letters, 1999, 6(1):1-3. 被引量:1
  • 9[9]FREEMAN D K, COSIER G, SOUTHCOTT C B, et al. The voice activity detector for the pan-European digital cellular mobile telephone service[A]. Proc Int Conf Acoust, Speech, Signal Processing[C]. Glasgow, UK, 1989. 369-372. 被引量:1
  • 10[10]SRINIVASAN K, GERSHO A. Voice activity detection for cellular net-works[A]. IEEE Speech Coding Workshop[C]. 1993. 85-86. 被引量:1

共引文献14

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部