Differences

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

--- course_outline [2007/07/31 19:53] – external edit 127.0.0.1
+++ course_outline [2011/11/17 02:36] (current) – hj
@@ Line 5: / Line 5: @@
 ===== Week 1 =====
-Your notes here.
+**Introduction**: application background; a big picture; speech sounds; spoken language
+(reading assignment)
 ===== Week 2 =====
-===== Midterm =====
+**Math Background**: probabilities; Bayes theorem; statistics; estimation; regression; hypothesis testing; entropy; mutual information; decision tree; optimization theory and convex optimization
-===== Drop Deadline =====
+===== Week 3 =====
+**Pattern Classification**: pattern classification & pattern verification; Bayesian decision theory
+===== Week 4 =====
+**Generative Models**: model estimation: maximum likelihood, Bayesian learning, EM algorithm; multivariate Gaussian, Gaussian mixture model, Multinomial, Markov Chain model, etc.
+===== Week 5 =====
+**Discriminative Models**: Linear discriminant functions; support vector machine (SVM); large margin classifiers; sparse kernel machines; Neural networks
+===== Week 6 =====
+**Hidden Markov Model (HMM)**: HMM vs. Markov chains; HMM concepts; Three algorithms: forward-backward; Viterbi decoding; Baum-Welch learning.
+===== Week 7  =====
+midterm presentation
+===== Week 8 =====
+**Automatic Speech Recognition (ASR) (I)**: Acoustic and Language Modeling:
+HMM for ASR;  ASR as an example of pattern classification;
+Acoustic modeling: HMM learning (ML, MAP, DT); parameter tying (decision tree based state tying); n-gram models: smoothing, learning, perplexity, class-based.
+===== Week 9 =====
+**Automatic Speech Recognition (ASR) (II)**: Search - why search; Viterbi decoding in a large HMM; beam search; tree-based lexicon; dynamic decoding; static decoding; weighted finite state transducer (WFST)
+===== Week 10 =====
+**Spoken Language Processing (I)**: text categorization
+classify text documents: call/email routing, topic detection, etc.
+vector-based approach, Naïve Bayes classifier; Bayesian networks, etc.
+(2) HMM applications: Statistical Part-of-Speech (POS) tagging;
+ Language understanding: hidden concept models.
+===== Week 11 =====
+**Spoken Language Processing (II)**: statistical machine translation
+ IBM’s models for machine translation: lexicon model, alignment model, language model
+ training process, generation & search
+===== Week 12 =====
+student presentation
-===== Week 13 =====
-===== Final Exam =====