期刊文献+

用于说话人识别的电话信道补偿技术 被引量:2

Telephone Channel Compensation Technique for Speaker Recognition
下载PDF
导出
摘要 在说话人识别平台上,针对碳键型电话产生的线性和非线性失真带来的影响,提出一个系统的补偿框架。通过研究电话信道对频谱包络的影响,从留数角度分析虚峰出现的原因,结合留数归一化方法和传统的倒谱均值减,对中间维的倒谱加以提升。实验结果表明,在训练环境和测试环境不匹配的情况下,该方法具有较好的顽健性。 Based on the speaker recognition system, the linear and nonlinear influences of carbon-button telephone channel are discussed. A compensation system is proposed to weaken those effects. By researching the frequency difference between telephone channel and traditional channel, the phantom formants are found, which can be reduced by normalization of its residues. Combined with CMS and ceptral lifter, the system is more robust under mismatch environment.
出处 《计算机工程》 CAS CSCD 北大核心 2008年第13期84-86,共3页 Computer Engineering
基金 黑龙江省博士后基金资助项目 哈尔滨工程大学基金资助项目
关键词 电话信道补偿 留数归一化 自适应成分加权 倒谱均值减 telephone channel compensation normalization of residues adaptive component weighting CMS
  • 相关文献

参考文献8

  • 1Hennansky H. RASTA Processing of Speech[J]. IEEE Transactions on Speech and Audio Processing, 1994, 2(4): 578-589.
  • 2Quatieri T F, Reynold D A, O'Leary G D. Estimation of Handset Nonlinearity with Application to Speaker Recognition[J]. IEEE Transactions on Speech and Audio Processing, 2000, 8(5): 567-584.
  • 3Tohkura Y. A Weighted Cepstral Distance Measure for Speech Recognition[J]. IEEE Transactions on Acoustics, Speech and Signal Processing, 1987, 35(10): 1414-1422.
  • 4Assaleh K T, Mammone R J. New LP-derived Features for Speaker Identification[J]. IEEE Transactions on Speech and Audio Processing, 1994, 2(4): 630-638.
  • 5侯风雷,张万军,王炳锡.电话信道对语音信号参数影响的研究[J].信息工程大学学报,2002,3(1):5-7. 被引量:2
  • 6周静芳,陈一宁,刘加,刘润生.说话人识别信道补偿技术HNSSM[J].清华大学学报(自然科学版),2004,44(7):942-945. 被引量:2
  • 7Menendez-Pidal X, Chen Ruxin, Wu Duanpei, et al. Compensation of Channel and Noise Distortions Combining Normalization and Speech Enhancement Techniques[J]. Speech Communication, 2001, 34(1/2): 115-126.
  • 8马治飞,徐望,王炳锡,王兴斌.基于概率模型和倒谱差分的特征补偿算法[J].计算机工程,2006,32(18):200-201. 被引量:1

二级参考文献13

  • 1L R拉宾纳 R W谢弗.语音信号数字处理[M].北京:科学出版社,1983..
  • 2Quatieri T F, Reynolds D A, O'Leary G C. Estimation of handset nonlinearity with application to speaker recognition [J]. IEEE Trans SAP, 2000, 8(5): 567-584.
  • 3Heck L P, Weintraub M. Handset-dependent background models for robust text-independent speaker recognition [A]. Proceedings of ICASSP [C]. Munich: IEEE, 1997.
  • 4Teunen R, Shahshahani B, Heck L. A model-based transformational approach to robust speaker recognition [A]. Proceedings of ICSLP [C]. Beijing: IEEE, 2000.
  • 5Reynolds D A, Quatieri T F. Speaker verification using adapted Gaussian mixture models [J]. Digital Signal Processing, 2000, 10: 19-41.
  • 6Martin A, Przybocki M. The NIST 1999 speaker recognition evaluation-An overview [J]. Digital Signal Processing, 2000, 10: 1-18.
  • 7Auckenthaler R, Carey M, Lloyd-Thoms H. Score normalization for text-independent speaker verification systems [J]. Digital Signal Processing, 2000, 10: 42-54.
  • 8Reynolds D A, Rose R C. Robust text-independent speaker identification using Gaussian mixture speaker models [J]. IEEE Trans SAP, 1995, 3(1): 72-83.
  • 9Kim H K,Rose R C.Cepstrum-domain Acoustic Feature Compensation Based on Decomposition of Speech and Noise for ASR in Noisy Environments[J].IEEE Trans.on Speech and Audio Processing,2003,11(5):435-446.
  • 10Neumeyer L,Weintraub M.Robust Speech Recognition in Noise Adaptation and Mapping Techniques[J].Signal Processing,1995:37(1-3):141-144.

共引文献1

同被引文献12

引证文献2

二级引证文献1

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