期刊文献+

一种基于倒谱特征的语音端点检测改进算法 被引量:8

An Improved Voice Activity Detection Method Based on Cepstral Features
在线阅读 下载PDF
导出
摘要 提出了一种应用语音倒谱特征参量的端点检测改进算法,对信噪比(SNR)从-10~20dB的带噪语音信号进行仿真实验,结果表明,所提方法能较为准确地检测到语音端点。 An improved voice activity detection method based on cepstral features is proposed. Simulation with a lot of noisy speech signals that ranging from -10 dB to 20 dB is made. The results show that the speech endpoints can be detected more accurately by proposed method in different SNR environments.
出处 《电声技术》 2006年第4期39-42,共4页 Audio Engineering
关键词 端点检测 倒谱距离 判决准则 voice activity detection cepstral distance discriminative rules
  • 相关文献

参考文献4

  • 1HAIGH J A,MASON J S.Robust Voice Activity Detection Using Cepstral Features[J].Computer,Co-mmunication,Control and Power Engineering.Proce-edings of the IEEE Region 10 Conference TENCON,1993,3:321-324.
  • 2RABINER L R,JUANG B H.Fundamentals of Speech Recognition[M].Prentice Hall PTR,1999.
  • 3BERITELLI F,SALVATORE C,SALVATORE S.A Low-complexity speech-pause detection algorithm for communication in noisy environments[J].Euro.Trans.Telecornms,2004,15:33-38.
  • 4胡光锐,韦晓东.基于倒谱特征的带噪语音端点检测[J].电子学报,2000,28(10):95-97. 被引量:72

二级参考文献1

  • 1Lee C H,Automatic Speech and speaker recognition-advanced topics,1996年

共引文献71

同被引文献38

引证文献8

二级引证文献24

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