期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

涨落复杂性测度在语音端点检测中的应用研究

Application of Fluctuation Complexity Measure to Speech Endpoint Detection
下载PDF
导出
摘要 目的研究基于涨落复杂性测度的语音特征提取,提高低信噪比语音端点检测的正确率和鲁棒性,从而改善语音处理和分析的性能。方法分析状态空间分割方法、窗长以及分区数对检测性能的影响。采用基于信息增益的复杂性行为度量,对含不同噪声类型,以及不同信噪比的各种中英文语音样本进行了对比实验。结果在低信噪比情况下,涨落复杂性测度比广泛应用的谱熵方法更有效。结论涨落复杂性测度技术可以较好地实现在动态噪声环境下对语音端点的检测。该方法鲁棒性好,算法实时性高。 Objective To find a useful index for real-time detecting of speech endpoint and improving the performance of speech processing under low SNR by analyzing fluctuation complexity of speech signals. Method The influence of state space partition method, window size and partition numbers on detecting performance was analyzed. The comparison experiments of speech signals corre- sponding to different SNR and noise type was designed using the measure of complexity behaviors based on the information gain. Result It was found that fluctuation complexity was more effective in detecting Iow-SNR speech than spectral entropy. Conclusion Fluctuation complexity is a valid feature to make speech/non-speech decision for the low SNR cases. The presented method can achieve robust performance and has a good real-time behavior.
作者 范影乐 武传艳 李轶 庞全
机构地区 杭州电子科技大学生物医学工程与仪器研究所 浙江大学生物医学工程与仪器学院
出处 《航天医学与医学工程》 CAS CSCD 北大核心 2006年第6期452-455,共4页 Space Medicine & Medical Engineering
基金 国家自然科学基金资助项目(60302027) 浙江省教育厅科研计划项目(20030620)
关键词 涨落 复杂性 声纹 语音端点检测 状态空间分割 fluctuation complexity voice print speech endpoint detection state space partition
分类号 R319 [医药卫生—基础医学] R857.3 [医药卫生—航空、航天与航海医学]
  • 相关文献

参考文献7

  • 1Rabiner L,Schafer R.Digital Processing of Speech Signals[M].Beijing:Science Publishing Center,1983.100-104
  • 2高慧,苏广川,陈善广.不同情绪状态下汉语语音的声学特征分析[J].航天医学与医学工程,2005,18(5):350-354. 被引量：23
  • 3Teager H,Teager S.Evidence for nonlinear production mechanisms in the vocal tract[C].In:Gersho A,eds.Speech Production and Speech Modeling,Boston:Kluwer Academic Publishers,1990.241-261.
  • 4王让定,柴佩琪.一个基于谱熵的语音端点检测改进方法[J].信息与控制,2004,33(1):77-81. 被引量：27
  • 5Bates J,Shepard H.Measuring complexity using information fluctuation[J].Physics Letters A,1993,172(66):416-425.
  • 6CHEN Zhongyong,QIAN Mingqi,WU Wenkai,et al.The study of fluctuation complexity for EEG signals[J].Automatica Sinca,2001,27(3):111-114.
  • 7GU Lingyun,Zahorian S.A new robust algorithm for isolated word endpoint detection[C].In:Anon,eds.Speech and Signal Processing.Orlando:Institute of Electrical and Electronics Engineers Inc,2002.4161-4167.

二级参考文献12

  • 1[1]Rabiner L R,Sambur M R.An algorithm for determining the endpoints of isnlated utterances [ J ].Bell System Technical Journal,1975,54(2):297～315.
  • 2[2]Li Q,Zheng J,Zhou Q,et al.A robust,real-time endpoint detector with energy normalization for ASR in adverse enviromments[A].IEEE International Conference on Acoustics,Speech,and Signal Proc essing (ICASSP 2001 ) [ C].Salt Lake City:2001,1.574～577.
  • 3[3]Shin W H,Lee B S,Lee Y K,et al.Speech/non-speech classification using multiple features for robust endpoint detection [ A ].Proceedings of the IEEE International Conference on Acoustics,Speech and Signal Processing [C].lstambul,Turkey:2000,3.1399～1402.
  • 4[4]Matin A,Charlet D,Mauuary L.Robust speech/non-speech detection using LDA applied to MFCC [A].IEEE International Conference on Acoustics,Speech,and Signal Processing (ICASSP 2001) [C].Salt LakeCity:2001,1.685～688.
  • 5[5]Kosmides E,Dermatas E,Kokkinakis G.Stochastic endpoint detection in noisy speech [ A ].International Workshop on Speech and Computer( SPECOM97 ) [ C ].Cluj-Napoca,Romania:1997.109～114.
  • 6[6]Shen J L,Hung J W,Lee L S.Robust entropy-based endpoint detection for speech recognition in noisy environments [ A ].International Conference on Spoken Language Processing (ICSLP-98)[C].Sydney,Australia:1998.232～238.
  • 7[7]Huang L S,Yang C H.A novel approach to robust speech endpoint detection in car environments [ A ].IEEE Intemational Conferenee on Acoustics,Speech,and Signal Processing ( ICASSP'00) [C].lstambul,Turkey:2000,3.1751～1754.
  • 8[8]Jia C,Xu B.An improved entropy-based endpoint detection algorithm [ A ].International Conference on Spoken Language Processing( ICSLP 2002) [ C].Taipei:2002.285～288.
  • 9[9]Bou-Ghazale S E,Assaleh K.A robust endpoint detection of speech for noisy environments with application to automatic speech recognition [ A ].IEEE International Conference on Acoustics,Speech,ani Signal Processing (ICASSP2002) [ C ].Orlando,USA:2002.1753～1756.
  • 10[10]Yamauchi J,Shimamura T.Noise estimation using high frequency regions for spectral subtraction [J].IEICE Transactions on Fundamentals of Electronics,Communications and Computer Sciences,2002,E85-A(3):723～727.

共引文献48

航天医学与医学工程
2006年 第6期

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