JM1: SPEECH and LANGUAGE PROCESSING
An Introduction to Natural Language Processing,
Computational Linguistics, and Speech Recognition
by Daniel Jurafsky and James H. Martin 
First Edition http://www.cs.colorado.edu/~martin/slp.html

JM2: Second Edition http://www.cs.colorado.edu/~martin/slp.html

JM3: Third Edition (draft) http://web.stanford.edu/~jurafsky/slp3/

Lecture 1 - First Lecture

JM1: 
7.5 Acoustic Processing of Speech . . . . . . .258
    Sound Waves . . . . . . . . . . . . . . . .258
    How to Interpret a Waveform . . . . . . . .259
    Spectra . . . . . . . . . . . . . . . . . .260
    Feature Extraction . . . . . . . .  . . . .264
7.6 Computing Acoustic Probabilities .. . . . .265-270

JM2:
Chapter 9: Automatic Speech Recognition

JM3: 
Chapter 29: Speech Recognition 


Lecture 2 - Phoneme modeling

JM1:
4.1 Speech Sounds and Phonetic Transcription . 92
    The Vocal Organs . . . . . . . . . . . . . 94-97
4.2 The Phoneme and Phonological Rules . . . . 102-104
7.7 Training a Speech Recognizer . . . . . . . 270-272
7.1 Speech Recognition Architecture . . . . . .235
7.2 Overview of Hidden Markov Models . . . . . 239-242
5.9 Weighted Automata . . . . . . . . . . . . .167
    Computing Likelihoods: The Forward Algorithm 169
    Decoding: The Viterbi Algorithm . . . . . .174
    Weighted Automata and Segmentation . . . . 178-180
D Training HMMs: The Forward-Backward Algorithm 841
  Continuous Probability Densities . . . . . . 847-850

JM2: 
Chapter 6: Hidden Markov and Maximum Entropy Models
Chapter 7: Phonetics
Chapter 9: Automatic Speech Recognition

JM3: 
Chapter 8 Hidden Markov Models
Chapter 29: Speech Recognition 


Lecture 3 - Language Modeling

JM1:
4.6 Mapping Text to Phones for TTS . . . . . . 119
    Pronunciation dictionaries . . . . . . . . 119-121
6.1 Counting Words in Corpora . . . . . . . .  191
6.2 Simple (Unsmoothed) N-grams . . . . . . . .194
    More on N-grams and their sensitivity . . .199
6.3 Smoothing . . . . . . . . . . . . . . . . .204
    Add-One Smoothing . . . . . . . . . . . . .205
    Witten-Bell Discounting . . . . . . . . . .208
    Good-Turing Discounting . . . . . . . . . .212
6.4 Backoff . . . . . . . . . . . . . . . . . .214
    Combining Backoff with Discounting . . . . 215
6.5 Deleted Interpolation . . . . . . . . . . .217-218
6.7 Entropy . . . . . . . . . . . . . . . . . .221
    Cross Entropy for Comparing Models . . . . 224-225

JM2: Chapter 4: Ngrams

JM3: 
Chapter 4: Ngrams
Chapter 7: Neural LMs

Lecture 4 - Continuous speech recognition

JM1:
7.3 The Viterbi Algorithm Revisited . . . . . .242 
7.4 Advanced Methods for Decoding . . . . . . .250
    A* Decoding . . . . . . . . . . . . . . . .252-258
5.6 Minimum Edit Distance . . . . . . . . . . .151-154

JM2:
Chapter 9: Automatic Speech Recognition
Chapter 10: Speech Recognition: Advanced Topics

JM3:
Chapter 29: Speech Recognition 

Lecture 5: End-to-end ASR