Differences

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

--- lecture_notes [2012/08/30 18:48] – hj
+++ lecture_notes [2012/11/07 19:34] – hj
@@ Line 1: / Line 1: @@
-  * Week 1: background introduction; speech and spoken language  (Weekly Reading:[[http://www.cse.yorku.ca/course_archive/2011-12/W/6328/Makhoul_BBN.pdf| W1]])
-  * Week 2: Math foundation: probabilities; Bayes theorem; statistics; Entropy; mutual information; decision tree; optimization (Weekly Reading: [[http://www.cse.yorku.ca/course_archive/2011-12/W/6328/Duda_AppMath.pdf|W2]])    (A useful online manual on [[http://www.ee.ic.ac.uk/hp/staff/dmb/matrix/calculus.html|Matrix Calculus]])
+  * {{:slp-f12-w1.pdf|Week 1}}: background introduction; speech and spoken language  (Weekly Reading:[[http://www.cse.yorku.ca/course_archive/2011-12/W/6328/Makhoul_BBN.pdf| W1]])
-  * Week 3: Bayesian decision theory; Discriminative Models: Linear discriminant functions, support vector machine (SVM); (Weekly Reading: [[http://www.cse.yorku.ca/course_archive/2011-12/W/6328/Bayes_decision_rule.pdf|W3_1]](part I), {{:svmtutorial.pdf|W3_2}}(part II))
+  * {{:cse6328-f12-w2.pdf|Week 2}}: Math foundation: probabilities; Bayes theorem; statistics; Entropy; mutual information; decision tree; optimization (Weekly Reading: [[http://www.cse.yorku.ca/course_archive/2011-12/W/6328/Duda_AppMath.pdf|W2]])    (A useful online manual on [[http://www.ee.ic.ac.uk/hp/staff/dmb/matrix/calculus.html|Matrix Calculus]])
-  * 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]])
+  * {{:cse6328-f12-w3.pdf|Week 3}}: Bayesian decision theory; Discriminative Models: Linear discriminant functions, support vector machine (SVM); (Weekly Reading: [[http://www.cse.yorku.ca/course_archive/2011-12/W/6328/Bayes_decision_rule.pdf|W3_1]](part I), {{:svmtutorial.pdf|W3_2}}(part II), {{:nn-bishop.pdf|W3_3}}(part III))
-  * {{:cse6328-w5.pdf|Week 5}}: Discriminative Learning; Bayesian Learning; Pattern Verification
+  * {{:cse6328-f12-w4.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_archive/2011-12/W/6328/EM_tutorial.pdf|W4]])
-  * {{: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-f12-w5.pdf|Week 5}}: Discriminative Learning; Bayesian Learning; Pattern Verification
-  * 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-f12-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}}, the full version of this paper is not required but is {{:rabiner1_hmm_asr.pdf|here}} for your reference)
-  * Week 9: Automatic Speech Recognition (ASR) (II): Language Modelling (LM); N-gram models: smoothing, learning, perplexity, class-based.
+  * {{:cse6328-f12-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}}})
-  * 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}})
+  * {{:cse6328_f12_w9.pdf|Week 9}}: Automatic Speech Recognition (ASR) (II): Language Modelling (LM); N-gram models: smoothing, learning, perplexity, class-based.
+  * 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)  (Additional slides for WFST)