期刊文献+

特征音方法在说话人识别中的应用

EigenVoice Means Used in Speech Recognition
下载PDF
导出
摘要 针对现实中训练数据不足的特点,在说话人建模时采用高斯混合模型—通用背景模型(Gaussian MarkovModel-Uniform Background Model,GMM-UBM),主要从说话人识别模型的自适应方法和参数估计方法两个方面,研究如何提高说话人识别系统的识别率.在说话人识别模型自适应方面,改进传统的用最大后验概率MAP(Maximum A Posterior Probability)得到说话人模型的方法,将语音识别中的最大似然线性回归MLLR(MaximumLikelihood Linear Regression)和基于特征音(EigenVoice,EV)的自适应方法,应用到说话人识别模型自适应当中,并将其与MAP方法进行比较. This thesis adopts GMM-UBM when model speaker recognition system considering of lacking data. In the aspect of adapting in speaker recognition system modeling and parameter estimating, attentions are put on researching in how to improve recognition rate. In the side of adapting in speaker recognition system modeling, we will ameliorate conventional MAP (Maximum A Posterior Probability) means to get speaker recognition model, apply MLLR (Maximum Likelihood Linear Regression) and EigenVoice adaptation ways which used in speech recognition into adapting in speaker recognition system modeling, and compare the results with MAP means.
作者 李荟 赵云敏
出处 《计算机系统应用》 2013年第8期176-179,共4页 Computer Systems & Applications
关键词 说话人辨认 最大后验概率 最大似然线性回归 特征音 speaker identification MAP MLLR eigen voice
  • 相关文献

参考文献4

  • 1俞一彪,王朔中.文本无关说话人识别的全特征矢量集模型及互信息评估方法[J].声学学报,2005,30(6):536-541. 被引量:7
  • 2Zhou G, Mikhael WB. Speaker Identification Based on Adaptive Discriminative Vector Quantisation.Vision, Image and Signal Processing, IEE Proc, 2012(6): 754-760.
  • 3Wolf MB, Park WKO, Blowers JC, Misty K. Toward Open-Set Text-Independent Speaker Identification in Tactical Communication. Computational Intelligence in Security and Defense Applications, Syracuse University, 2011:7-14.
  • 4Barras C, Meignier XZ, Gauvian S, Multistage JL. Speaker Diarization of Broadcast News. Audio, Speech an Language Processing, IEEE, 2011 (5):1505-1512.

二级参考文献13

  • 1俞一彪,王朔中.基于互信息匹配模型的说话人识别[J].声学学报,2004,29(5):462-466. 被引量:8
  • 2Chen C T, Chen C. Efficient genetic algorithm of codebook design for text-independent speaker recognition. IEICE,2002, E85-A(11): 2529-2531.
  • 3Lee Y -T. Information-theoretic distortion measures for speech recognition. IEEE-ASSP, 1991; 39:330-335.
  • 4Okawa S, Kobayashi T, Shirai K. Automatic training of phoneme dictionary based on mutual information criterion.ICASSP, 1994:241-244.
  • 5Bahl L R, Brown P F. Maximum mutual information estimation of hidden Markov model parameters for speech recognition. ICASSP, 1986:49-52.
  • 6Shaughnessy D O. Speech communications-human and machine. IEEE Press, NJ., 2000:378-383.
  • 7Naik J. Speaker verification: A tutorial. IEEE Commun.Mag., 1990; 28(1): 42-48.
  • 8Campbell J P. Speaker recognition: A tutorial. IEEE Proc., 1997; 85(9): 1436-1462.
  • 9Reynolds D A, Rose R C. Robust text-independent speaker identification using Gaussian Mixture Speaker Models.IEEE Speech and Audio, 1995; 3(1): 72-83.
  • 10Tanprasert C, Achariyakulporn V. Comparative study of GMM, DTW and ANN on Thai speaker identification system. In: Proc. ICSLP, 2000 (Paper No.00718).

共引文献6

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