收稿日期: 2002-06-25
网络出版日期: 2003-07-10
基金资助
科技部中小企业创新基金资助项目(01C26221100019)
Estimations of Convolution Noise in PMC
Received date: 2002-06-25
Online published: 2003-07-10
Supported by
null
缪彩练 , 王阳生 . 并行模型组合方法中卷积噪声的估计方法[J]. 中国科学院大学学报, 2003 , 20(4) : 425 -432 . DOI: 10.7523/j.issn.2095-6134.2003.4.005
The envi ronment adaptive method plays an important part in improving the robustness of automatic speech recognition.PMC is reviewed briefly and improved to achieve bet ter performance in real adverse environment.The experiments have been done based on Cambridge' s HTK toolkit to implement the continuous Mandarin digit recognition in noisy environment
Key words： PMC; convolutional and additive noise; EMest imation; dynamic parameter
［1］Moore. Hidden Markov Model Decomposition of Speech and Noise. In: Proc ICASSP' 1990. 1990. 845～848
［2］P J Moreno. Speech Recognition in Noisy Environments: [Ph. D. Thesis ]. Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, 1996
［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］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］A Acero, L Deng, T Kristjansson, J Zhang. Hmm Adaptation Using Vector Taylor Series For Noisy Speech Recognition. In: Proceedings of ICSLP, 2000
［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］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］Young S, et al, The HTKBook; http:// htk. Eng. Cam. Ac. Uk/, 2001
［9］X D Huang, A Acero, H Hon. Spoken Language Processing. Prentice Hall, 2000
［10］M J F Gales. Predictive Model-Based Compensation Schemes for Robust Speech Recognition. Speech Communication, 1998, 25: 49～74
［11］Yun-Xin Zhao. Frequency-Domain Maximum Likelihood Estimation for Automatic Speech Recognition in Additive and Convolutive Noises. IEEE Transactions on Speech and Audio Processing, 2000, 8:255～266
［12］Tetsuya Takiguchi, Satoshi Nakamura, Kiyohiro Shikano. HMM-Separation-Based Speech Recognition for a Distant Moving Speaker. IEEE Transactions on Speech and Audio Processing, 2001,9(2): 127～140
［13］P C Woodland, M J F Gales, D Pye. Improving Environmental Robustness in Large Vocabulary Speech Recognition. In: Proc ICASSP＇1996. Atlanta, GA, 1996.65～68
［14］Rahim M G, B H Juangv. Signal Bias Removal by Maximum Likelihood Estimation for Robust Telephone Speech Recognition. IEEE Transactions on Speech and Audio Processing, 1996, 4(1 ) :19～30
［15］Ananth Sanar Hui. A Maximum-Likelihood Approach to Stochastic Matching for Robust Speech Recogntion. IEEE Transactions on Speech and Audio Processing, 1996,4(3):190～202
/
| 〈 |
|
〉 |
