Speech Recognition
Fall 2005
Tuesdays, 9:10 ~12:00 AM
Instructor: Berlin Chen (陳柏琳 助理教授)Tentative Topic List and Schedule:
| 9/13 |
Course Overview &
Introduction |
||
| 9/20 |
Hidden
Markov Models (1/2) |
HW-1:Problems
1&2 for HMM Due: 10/11 HW-1B:Deriving Backward Algorithm (opt.) |
|
| 9/27 |
Hidden Markov Models (2/2) |
HW-2A:Problem
3 for HMM Due: 10/18 |
|
| 10/4 |
Spoken
Language Structure |
HW-2B:Counting
Word Error Rates (opt.) Reference Files, Test Files |
|
| 10/11 |
Introduction to Isolated Word Recognition |
HW-3A:
Drawing the Spectrograms
(opt.) |
|
| 10/18 |
Acoustic Modeling |
HW-3B:
Isolated Word Recognition |
|
| 10/25 |
HTK Toolkit |
HW-4:
the Use of HTK Toolkit |
|
| 11/1 |
Statistical Language Modeling |
||
| 11/8 |
SRILM Toolkit |
HW-5:
the
Use of SRILM Toolkit |
|
| 11/15 |
Midterm |
||
| 11/22 |
Digit Recognition,
Word Recognition and Keyword Spotting |
||
| 11/29 |
Large Vocabulary
Continuous Speech Recognition (1/2) |
||
| 12/6 |
Large Vocabulary
Continuous Speech Recognition (2/2) |
HW-6:
Syllable Decoding with Bigram LM
(Syllable bigrams should be trained by SRILM) |
|
| 12/13 |
Digital Signal
Processing Related to Speech Recognition (1/2) |
||
| 12/20 |
Digital Signal
Processing Related to Speech Recognition (2/2) |
||
| 12/27 |
Speech Signal
Representations |
||
| 1/3 |
Speech Enhancement
and Robustness |
||
| 1/10 |
FINAL |
||
| Discriminative Training Approaches for Continuous Speech Recognition |
Textbook:
1. X. Huang, A. Acero, H. Hon, “Spoken Language Processing,” Prentice Hall, 2001 (全華代理)
2. W. Chou,. B.H. Juang. Pattern Recognition in Speech and Language Processing. CRC Press, 2003
3. C. Manning and H. Schutze, Foundations of Statistical Natural Language Processing, MIT Press, 1999.References:
Books:
1. T. F. Quatieri,“Discrete-Time Speech Signal Processing - Principles and Practice,” Prentice Hall, 2002
2. J. R. Deller, J. H. L. Hansen, J. G. Proakis, “Discrete-Time Processing of Speech Signals,” IEEE Press, 2000
3. F. Jelinek, "Statistical Methods for Speech Recognition," The MIT Press, 1999
4. S. Young et al., “The HTK Book”, Version 3.2, 2002. "http://htk.eng.cam.ac.uk"
5. L. Rabiner, B.H. Juang, “Fundamentals of Speech Recognition”, Prentice Hall, 1993Papers:
1. Lawrence Rabiner. The Power of Speech. Science, Vol. 301, pp. 1494-1495, Sep. 2003.
2. L. Rabiner, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition,”
Proceedings of the IEEE, vol. 77, No. 2, February 1989
3. A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from incomplete data via the EM algorithm,"
J. Royal Star. Soc., Series B, vol. 39, pp. 1-38, 1977
4. Jeff 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
5. J. W. Picone, “Signal modeling techniques in speech recognition,” proceedings of the
IEEE, September 1993, pp. 1215-1247
6. R. Rosenfeld, ”Two Decades of Statistical Language Modeling: Where Do We Go from
Here?,” Proceedings of IEEE, August, 2000
7. H. Ney, “Progress in Dynamic Programming Search for LVCSR,” Proceedings of the IEEE, August 200
8. H. Hermansky, "Should Recognizers Have Ears?", Speech Communication, 25(1-3), 1998.
9. Lawrence Rabiner. The Power of Speech. Science, Vol. 301, pp. 1494-1495, Sep. 2003.
10. J. R. Bellegarda, "Statistical Language Model Adaptation: Review and Perspectives," Speech Communication, vol. 42, no.1, pp. 93-108, 2004.(a1) Proceedings of IEEE, vol. 88, no. 8, August, 2000 (Special Issue on Spoken Language Processing)
(a2) IEEE Signal Processing Magazine, vol. 22, no. 5, September, 2005 (Special Issue on Speech Technology and Systems in Human-Machine Communication)