Differences

This shows you the differences between two versions of the page.

--- lecture_notes [2012/02/02 03:39] – hj
+++ lecture_notes [2012/03/21 14:06] (current) – hj
@@ Line 7: / Line 7: @@
   * {{:cse6328_w4_new.pdf|Week 4}}: Generative Models; model estimation; maximum likelihood, EM algorithm; multivariate Gaussian, Gaussian mixture model, Multinomial, Markov Chain model; (Weekly Reading: [[http://www.cse.yorku.ca/course/6328/EM_tutorial.pdf|W4]])
-  * Week 5: Discriminative Learning; Bayesian Learning; Pattern Verification
+  * {{:cse6328-w5.pdf|Week 5}}: Discriminative Learning; Bayesian Learning; Pattern Verification
+  * {{:cse6328_w6.pdf|Week 6}}: Hidden Markov Model (HMM): HMM vs. Markov chains; HMM concepts; Three algorithms (forward-backward, Viterbi decoding, Baum-Welch learning)  (Weekly Reading: {{:rabiner1_hmm_asr_part1.pdf|W6}})
+  * {{:cse6328-w8.pdf|Week 8}}: Automatic Speech Recognition (ASR) (I): ASR introduction; ASR as an example of pattern classification; Acoustic modeling: parameter tying (decision tree based state tying); (Weekly Reading: {{:htkbook31_part1.pdf|W8}})
+  * {{:cse6328-w9.pdf|Week 9}}: Automatic Speech Recognition (ASR) (II): Language Modelling (LM); N-gram models: smoothing, learning, perplexity, class-based.
+  * {{:cse6328_w10.pdf|Week 10}}: Automatic Speech Recognition (ASR) (III): Search - why search; Search space in n-gram LM; Viterbi decoding in a large HMM; beam search; tree-based lexicon; dynamic decoding; static decoding; weighted finite state transducer (WFST)  ({{:wfst-tutorial.pdf|Additional slides for WFST}})