期刊文献+

基于时频ICA的PMC模型卷积噪声估计方法研究

A study on PMC convolutive noise estimation method based on time/frequency ICA
下载PDF
导出
摘要 为提高卷积环境下语音识别系统的鲁棒性,提出了一种基于时/频ICA(independent component analysis)的卷积噪声模型估计方法.所提算法首先使用ICA方法从含噪语音信号中提取纯净语音信号的短时功率谱,然后在MEL滤波器组域内将含噪语音的短时谱减去纯净语音的短时谱,并根据去噪后卷积噪声的短时谱估算其HMM(hidden markov model)模型.在仿真和真实环境下进行了语音识别实验,其识别正确率相比较传统的卷积噪声估计方法分别提升了4.70%和4.75%.实验结果表明,论文所提算法能够实现对卷积噪声的精确估计,并有效提升卷积噪声环境下语音识别系统的性能. In order to improve robustness of speech recognition system in convolutive environment, a convolutive noise estimation method based on time/frequency ICA (independent component analysis) (TD-ICA) was proposed in the paper. The algorithm firstly separated the short-time spectrum of speech and noise by TI)-ICA algorithm, and then the noise short-time spectrum was acquired by subtracting the estimated clean speech short time spectrum from the noisy speech in the mel-scale filter bank domain. Finally, an HMM (hidden Markov model) of convolutive noise was established based on the noise short-time spectrum. Experiments have been carried out in simulation and real environment, experiential results revealed that the proposed algorithm obtained the relative increasing of 4. 70% and 4. 75% compared with conventional noise estimation method, which validated the accuracy of estimated noise signal and proved that the proposed algorithm could effectively improve recognition ratio in convolutive noise environment.
出处 《安徽大学学报(自然科学版)》 CAS 北大核心 2016年第5期24-31,共8页 Journal of Anhui University(Natural Science Edition)
基金 国家自然科学基金资助项目(61401002) 安徽省自然科学基金资助项目(1408085QF125) 安徽省高校省级自然科学研究重点项目(KJ2014A011) 光电获取与控制教育部重点实验室开放课题(OEIAM201401)
关键词 语音 独立分量分析 PMC(parallel model combination)模型 卷积噪声 speech ICA PMC(parallel model combination) model convolution noise
  • 相关文献

参考文献17

  • 1GALES M J F, YOUNG S J. Robust continuous speech recognition using parallel model combination[J]. Speech and Audio Processing, IEEE Transactions, 1996, 4 (5): 352-359.
  • 2MINAMI Y, FRUUI S. A maximum likelihood procedure for a universal adaptation method based on HMM compositionEC]//Acoustics, Speech, and Signal Processing, ICASSP-95, International Conference on IEEE, 1995, 1: 129-132. V.
  • 3ARGA A P, MOORE R K. Hidden Markov model decomposition of speech and noise[C~// Acoustics, Speech, and Signal Processing, ICASSP-90, International Conference on IEEE, 1990: 845-848.
  • 4SIM K C. Approximated Parallel Model Combination for efficient noise-robust speech recognition[C]// Acoustics, Speech and Signal Processing (ICASSP), IEEE International Conference on IEEE, 2013.. 7383-7387.
  • 5YU D, DENG L. Hidden markov models and the variants EC]//Automatic Speech Recognition, Springer London, 2015: 23-54.
  • 6RAO K S, SARKAR S. Robust speaker verification: a review[C]//Robust Speaker Recognition in Noisy Environments, Springer International Publishing, 2014.- 13-27.
  • 7ALI U, YAHYA K M, JAN T, et al. Blind separation of convolutive speech mixtures with background interference employing a Hybrid approach With ICA ~ PCA[J]. Sindh University Research Journal-SURJ (Science Series), 2014, 46 (2) :256-280.
  • 8ASAEI A, BOURLARD H, TAGHIZADEH M J, et al. Computational methods for underdetermined convolutive speech localization and separation via model-based sparse component analysis[J]. Speech Communication, 2015: 201-217.
  • 9HYVARINEN A, KARHUNEN J, OJA E. Independent component anaiysisEM]. Manhattan: John Wiley Sons, 2004.
  • 10张磊,张道信,吴小培.基于独立分量分析的心理作业诱发脑电特征增强[J].安徽大学学报(自然科学版),2008,32(2):39-43. 被引量:2

二级参考文献5

  • 1Keirn L,Aunon J I.A new mode of communication between man and his surroundings[J].IEEE Trans on BME,1990,37(12):1129-1150.
  • 2Lee T W.Independent Component analysis -theory and application[M].Kluwer,1998:27-64.
  • 3Scott Making.Independent Component Analysis of Electroencephalographic Data.Adwances in Neural Information Processing Systems 8[M].MIT Press,Cambridge MA,1996:145-151.
  • 4Andreas Ziehe.Artifact reduction in magnetoneurography based on Time-Delayed Second-Order Correction[J].IEEE Trans on BME,2000,47 (1):75-87.
  • 5Richard Vigario.Independent component approach to the analysis of EEG and MEG Rrecording[J].IEEE Trans,on BME,2000,47(5):589 -593.

共引文献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