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

基于概率统计直方图的压缩域说话人识别

Compressed-Domain Automatic Speaker Recognition Based on Probabilistic Stochastic Histogram
下载PDF
导出
摘要 压缩域说话人识别算法(Compressed-domain automatic speaker recognition,CD-ASR)即从压缩语音数据中直接提取压缩参数进行说话人识别,无需参数译码和波形合成。本文提出了基于概率统计直方图的VoIP压缩域说话人识别算法,包括矢量量化统计直方图和高斯混合模型统计直方图两种方法。在给出了G.729,G.723.1(6.3 kb/s),G.723.1(5.3 kb/s)压缩码流的压缩域特征提取方案后,分别以矢量量化统计直方图和高斯混合模型统计直方图作为识别模型进行说话人识别。实验结果表明,概率统计直方图法比在压缩码流中提取同样识别参数的GMM模型,识别率有很大提高。 Compressed-domain automatic speaker recognition （CD-ASR） extracts features directly from the coded speech bit-stream to avoid decoding the parameters and resynthesizing the speech waveform. In this paper, a compressed-domain speaker recognition approach is pro- posed based on the probabilistic stochastic histogram. Firstly, the compressed-domain feature extraction schemes of G. 729,G. 723.1 （6.3 kb/s）, G723.1（5.3 kb/s） compressed bit streams are described. Then, the speaker recognition algorithms are presented based on vector quantization probabilistic stochastic histogram （VQPSH） and Gaussian mixture model probabilistic stochastic histogram（GMMPSH）. Experimental results show that the probabilistic stochastic histogram algorithm is superior to classical GMM when using the same compressed-domain feature extraction algorithms.
作者 屈丹 闫红刚 唐晖 王炳锡
机构地区 解放军信息工程大学信息工程学院
出处 《数据采集与处理》 CSCD 北大核心 2009年第5期594-599,共6页 Journal of Data Acquisition and Processing
基金 国家"八六三"高技术研究发展计划(2006AA01Z146)资助项目
关键词 压缩域说话人识别 矢量量化概率统计直方图 高斯混合模型概率统计直方图 compressed-domain automatic speaker recognition （CD-ASR） vector quantization probabilistic stochastic histogram（VQPSH） Gaussian mixture model probabilistic stochastic histogram （GMMPSH）
分类号 TN912.3 [电子电信—通信与信息系统]
  • 相关文献

参考文献9

  • 1Petracca M,Servetti A, Demartin J C. Performance analysis of compressed-domain automatic speaker recognition as a function of speech coding technique and bit rate [C]//Proceedings of International Conference on Multimedia and Expo (ICME). Toronto, Canada:IEEE Press,2006:1393-1396.
  • 2Dunn R B, Quatieri T F, Reynolds D A, et al. Speaker recognition from coded speech in matched and mismatched conditions [C]//Proceedings of Speaker Recognition Workshop'1. Grete, Greece: [s.n.], 2001: 115-120.
  • 3Quatieri T F, Dunn R B, Reynolds D A, et al. Speaker recognition using G. 729 speech codec parameters [C]//Proceedings of IEEE, International Conference on Audio, Speech and Signal Processing. Istanbul, Turkey:IEEE Press, 2000: 1089-1093.
  • 4Aggarwal C C, Olshefski D, Saha D, et al. CSR: speaker recognition from compressed VoIP packet stream[C]//Proceedings of International Conference on Multimedia and Expo (ICME). Amsterdam, Holand : IEEE Press, 2005 : 970-973.
  • 5Petracca M, Servetti A, Demartin J C. Low-complextity automatic speaker recognition in the compressed GSM-AMR domain[C]//Proceedings of International Conference on Multimedia and Expo (ICME). Amsterdam, Holand:IEEE Press, 2005: 662-665.
  • 6ITU-T H. 323 2000. Packet-based multimedia communications systems[S]. Genevese: ITU-T,2000.
  • 7ITU-T Recommendation G. 729-1996. Coding of speech at 8 kbit/s using conjugate-structure algebraic-code-excited linear-prediction (CS-ACELP)[S]. Helsinki.. WTSC Resolution, 1996.
  • 8ITU-T Recommendation G. 723.1-1996. Dual rate speech coder for multimedia communications trans- mitting at 5.3 and 6.3 kbit/s [S]. Helsinki: WTSC Resolution, 1996.
  • 9屈丹,王炳锡,魏鑫.基于GMM-UBM模型的语言辨识研究[J].信号处理,2003,19(1):85-88. 被引量：10

二级参考文献11

  • 1Y. K. Muthusamy, E. Barnard and R. A. Cole, "Reviewing Automatic Language Identification", IEEE Signal Processing Magazine, October 1994.
  • 2Berkling, K.M., Arai, T., Barnard, E., Cole, R.A., 1994.Analysis of phoneme-based features for language identification. In: International Conference on Acoustics,Speech, and Signal Processing, Vol. 1, Aprikl 1994, pp.289-292.
  • 3M.A. Zissman. Language identification using phoneme recognition phonotactic language modeling. In Proceedings 1995 IEEE International Conference onAcoustics,Speech, and Signal Processing, pages 3503- 3506, May 1995.
  • 4J. Narvratil and Wemer Zuhlke. Double bigramdecoding in Phonotactic language identification. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing 97, Munique,Germany, April 1997.
  • 5Y. K. Muthusamy, R. A. Cole, and B. T. Oshika. The OGI Multi-language telephone speech corpus. Technical report,Center for Spoken Language Understanding Oregon Graduate Institute of Science and Technology, Portland,1993.
  • 6D.A. Reynolds, T. E Quaffed, and R. B. Dunn. Speaker verification using adapted Gaussian mixture models.Digital Signal Processing, Vol. 10, pp 19-41, 2000.
  • 7D.A. Reynolds, and R.C. Rose, Rosust text-independence speaker identification using Gaussian mixture speaker models. IEEE Transactions on Speech and Audio Processing, vol.3, No. 1, pp72-83.
  • 8A. E. Rosenberg and S. Parthasarathy, Speaker background models for connected digit password speaker verification. In Proceedings of the International Conference on Acoustics, Speech and Signal Processing,pp 81-84, 1996
  • 9J. L. Gauvain and C.H. Lee, Maximum a postedori estimation for multivariate Gaussian mixture observations of Markov chains, IEEE Trans. Speech Audio Process.Vol.2, pp 291-298,1994.
  • 10M. A. Zissman, "Comparison of four approaches to automatic language identification of telephone speech",IEEE Trans. Speech Audio Process. Vol. 4, pp 31-44.

共引文献9

数据采集与处理
2009年 第5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