期刊文献+

并行模型组合方法中卷积噪声的估计方法

Estimations of Convolution Noise in PMC
下载PDF
导出
摘要 由于实际环境中各种噪声的干扰 ,语音识别的准确率会受到不同程度的影响 ,因此 ,鲁棒性技术已成为语音识别的一个研究热点。其中 ,并行模型组合方法 (PMC)在提高模型对环境的适应性方面发挥着重要作用。分析了PMC中如何解决其技术难点的一些方法 ,并作了相应的优化改进 ,从而使PMC方法能适用于较为复杂的实际情况。实验利用了剑桥大学的HTK语音识别工具包 ,并加入自行开发的算法 ,可用于对 0~ 91 0个中文数字组成的数字串进行连续语音识别。结果表明 ,在不同的噪声环境下 。 The environment adaptive method playsan important part in improving the robustness of automatic speech recognition. PMC is reviewed briefly and improved to achieve better performance in real adverse environment. The experiments have been done based on Cambridge'sHTK toolkit to implement the continuous Mandarin digit recognition in noisy environment.
出处 《中国科学院研究生院学报》 CAS CSCD 2003年第4期425-432,共8页 Journal of the Graduate School of the Chinese Academy of Sciences
基金 科技部中小企业创新基金资助项目 ( 0 1C2 62 2 110 0 0 19)
关键词 PMC方法 卷积噪声与加性噪声 EM估计 动态参数 PMC, convolutional and additive noise, EM estimation, dynamic parameter
  • 相关文献

参考文献15

  • 1[1]Moore. Hidden Markov Model Decomposition of Speech and Noise. In: Proc ICASSP' 1990. 1990. 845~848
  • 2[2]P J Moreno. Speech Recognition in Noisy Environments: [Ph. D. Thesis ]. Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, 1996
  • 3[3]Tai-Hwei Hwang, Hsiao-Chuan Wang. A Fast Algorithm for Parallel Model Combination for Noisy Speech Recognition. Computer Speech and Language, 2000, 14(2) :81~100
  • 4[4]R Sarikaya, J H L Hansen. PCA-PMC: A Novel Use of A Priori Knowledge for Fast Parallel Model Combination. In: Proceedings ICASSP: No. 2. Istanbul, Turkey. 2000. 1113 ~ 1116
  • 5[5]A Acero, L Deng, T Kristjansson, J Zhang. Hmm Adaptation Using Vector Taylor Series For Noisy Speech Recognition. In: Proceedings of ICSLP, 2000
  • 6[6]M J F Gales. The Generation and Use of Regression Class Trees for MLLR Adaptation. Technical Report CUED/F-INFENG/TR.263. Cambridge University Engineering Department, 1996
  • 7[7]S J Doh. Enhancements to Transformation-Based Speaker Adaptation: Principal Component and Inter-Class Maximum Likelihood Linear Regression: [Ph. D. Thesis]. ECE Department, CMU. 2000
  • 8[8]Young S, et al, The HTKBook; http:// htk. Eng. Cam. Ac. Uk/, 2001
  • 9[9]X D Huang, A Acero, H Hon. Spoken Language Processing. Prentice Hall, 2000
  • 10[10]M J F Gales. Predictive Model-Based Compensation Schemes for Robust Speech Recognition. Speech Communication, 1998, 25: 49~74

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