Speech Recognition

Spring 2009
Fridays, 9:10 ~12:00 AM
Instructor: Dr.
Berlin Chen (陳柏琳)

Topic List and Schedule:

02/27 Course Overview & Introduction
03/06   Hidden Markov Models (I)  
03/13   Hidden Markov Models (II)
Maximum Likelihood Estimation (MLE) for Probability Distributions
HW-01& 02: Three Problems of HMM (Due: 04/10)
03/20   Spoken Language Structure  
03/27   Acoustic Modeling (I)  
04/03   Acoustic Modeling (Decision Tree Learning) (II)  
04/10   Statistical Language Modeling  (especially n-gram modeling)  
04/17   Statistical Language Modeling  (especially n-gram modeling)  
04/24   ICASSP 2009  
05/01   Introduction to Hidden Markov Toolkit (HTK) , Installation of HTK HW-03: Using HTK for Continuous Syllable Recognition  (Due: 05/22)
05/08   Isolated Word Recognition, Keyword Spotting, and Continuous Speech Recognition
Large Vocabulary Continuous Speech Recognition (LVCSR)
Take-Home Exercise-01: Isolated Word Recognition (Explanation)
05/15   Midterm  
05/22   Introduction to SRILM Toolkit Take-Home Exercise-02: Using SRILM
06/05   Speech Signal Representations  
06/12   Speech Enhancement and Robustness
Tutorial of Building an LVCSR System using HTK
HW-04: LVCSR Using HTK  (Due: 06/30)
06/19   Linear Prediction Analysis (Digital Signal Processing for Speech Recognition)  

Reference Books:

§   Jacob Benesty (ed.), M. Mohan Sondhi (ed.), Yiteng Huang (ed.), Springer Handbook of Speech Processing, Springer, 2007  
§   X. Huang, A. Acero, H. Hon, Spoken Language Processing: A Guide to Theory, Algorithm and System Development, Prentice Hall, 2001  
§   L. Rabiner, B.H. Juang, “Fundamentals of Speech Recognition”, Prentice Hall, 1993  
§   M.J.F. Gales and S.J. Young. The Application of Hidden Markov Models in Speech Recognition. Foundations and Trends in Signal Processing, 2008  
§   L. Rabiner and R.W. Schafer. Introduction to Digital Speech Processing. Foundations and Trends in Signal Processing, 2007  
§   W. Chou,. B.H. Juang. Pattern Recognition in Speech and Language Processing. CRC Press, 2003  
§   S. Young et al., “The HTK Book”, Version 3.2, 2002. "http://htk.eng.cam.ac.uk"  
§   T. F. Quatieri,“Discrete-Time Speech Signal Processing - Principles and Practice,” Prentice Hall, 2002  
§   F. Jelinek, "Statistical Methods for Speech Recognition," The MIT Press, 1999  
§   J. R. Deller, J. H. L. Hansen, J. G. Proakis, “Discrete-Time Processing of Speech Signals,” IEEE Press, 2000  
§   C. Manning and H. Schutze, Foundations of Statistical Natural Language Processing, MIT Press, 1999  
§   J. Bellegarda, Latent Semantic Mapping: Principles & Applications (Synthesis Lectures on Speech and Audio Processing), 2008  
§   T. K. Landauer, D. S. McNamara, S. Dennis, W. Kintsch (eds.) , Handbook of Latent Semantic Analysis, Lawrence Erlbaum, 2007  
§   Ethem Alpaydin, Introduction to Machine Learning, MIT Press, 2004  
§   D. P. Bertsekas, J. N. Tsitsiklis, “Introduction to Probability,” Athena Scientific, 2002  

  Reference Papers:

§   L. Rabiner. The Power of Speech. Science, Vol. 301, pp. 1494-1495, Sep. 2003.  
§   Baker, J.M.et al., Research Developments and directions in speech recognition and understanding, part 1, IEEE Signal Processing Magazine 25(3), May 2009.  
§   Baker, J.M.et al., Research Developments and directions in speech recognition and understanding, part 2, IEEE Signal Processing Magazine 25(4), July 2009.  
§   M. Ostendorf, Speech Technology and Information Access, IEEE Signal Processing Magazine 25(3), May 2008.  
§   L. Rabiner, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition,” Proceedings of the IEEE, vol. 77, No. 2, February 1989  
§   A. V. Oppenheim and R. W. Schafer, "From Frequency to Quefrency: A History of the Cepstrum," IEEE Signal Processing Magazine 21(5), September 2004.  
§   A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," Journal of the Royal Statistical Society. Series B (Methodological), Vol. 39, No. 1,  1977  
§   J. A. Bilmes  "A Gentle Tutorial of the EM Algorithm and its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models," U.C. Berkeley TR-97-021  
§   J. W. Picone, “Signal modeling techniques in speech recognition,” proceedings of the IEEE, September 1993, pp. 1215-1247  
§   R. Rosenfeld, ”Two Decades of Statistical Language Modeling: Where Do We Go from Here?,” Proceedings of IEEE, August, 2000  
§   H. Ney, “Progress in Dynamic Programming Search for LVCSR,” Proceedings of the IEEE, August 2000  
§   Aubert, X. L., "An Overview of Decoding Techniques for Large Vocabulary Continuous Speech Recognition," Computer Speech and Language, vol. 16, 2002, pp. 89-114.  
§   H. Hermansky, "Should Recognizers Have Ears?", Speech Communication, 25(1-3), Speech Communication, 25(1-3), 1998.  
§   J. R. Bellegarda, "Statistical Language Model Adaptation: Review and Perspectives," Speech Communication, vol. 42, no.1, pp. 93-108, 2004.  
§   B. Roark, "A survey of discriminative language modeling approaches for large vocabulary continuous speech recognition," in Large Margin and Kernel Approaches to Speech and Speaker Recognition, J. Keshet and S. Bengio (Eds.), Wiley, 2009.  
§   L. Rabiner, B.H. Juang, "Speech Recognition: Statistical Methods," Encyclopedia of Language & Linguistics, pp. 1-18, 2006.  
§    P. Nguyen, "TechWare: Speech recognition software and resources on the web," IEEE Signal Processing Magazine 25(3), May 2009.  
§   J. B. Allen, F. Li, "Speech Perception and Cochlear Signal Processing," IEEE Signal Processing Magazine 25(4), July 2009.  
§   A. Orlitsky, N. P. Santhanam, J. Zhang, "Always Good Turing: Asymptotically Optimal Probability Estimation," Science, 17 October 2003.  
  Proceedings of IEEE 88(8), August, 2000 (Special Issue on Spoken Language Processing)  
  IEEE Signal Processing Magazine 22(5), September 2005  (Special Issue on Speech Technology and Systems in Human-Machine Communication)  
  IEEE Signal Processing Magazine 25(3), May 2008  (Special Issue on Spoken Language Technology)  

Reference Presentations:

§   J. Droppo, Noise Robust Automatic Speech Recognition, a comprehensive tutorial talk given at EUSIPCO 2008  
§   B. Chen, Latent Semantic Approaches for Information Retrieval and Language Modeling, a talk given at Telecommunication Laboratories, Chunghwa Telecom Co., Ltd., 2008  
§   B. Chen, Recent Developments in Chinese Spoken Document Search and Distillation, a talk given at Google Taipei, 2009  


林士翔同學 (博二)
     – E-mail: shlin@csie.ntnu.edu.tw
     – Tel: 29322411ext 208 (資工系208室)