Courses:

Automatic Speech Recognition >> Content Detail



Lecture Notes



Lecture Notes

Media player software, such as Quicktime® PlayerRealOne™ Player, or Windows Media® Player, is required to run the .wav files in this section.
This section contains a complete set of lecture slides for the course, including guest lectures. Lectures 3, 4, and 6 have audio links to speech samples presented during the lectures.


WEEK #LEC #TOPICS
11
2
Course Overview (PDF)
Acoustic Theory of Speech Production (PDF - 1.4 MB)
23
4
Speech Sounds (PDF - 3.6 MB)
Speech Sounds (continued)
35
6
Signal Representation (PDF - 1.9 MB)
Vector Quantization (PDF - 1.8 MB)
47
8
Pattern Classification (1) (PDF - 1.1 MB)
Pattern Classification (2) (PDF)
59
10
Search (PDF)
Hidden Markov Modeling (1) (PDF)
611
12
Language Modeling (PDF)
Language Modeling (continued)
713Guest Lecture by Karen Livescu: Graphical Models (PDF)
Quiz 1
814
15
Guest Lecture by Rita Singh: Hidden Markov Modeling (2) (PDF - 2.1 MB)
Guest Lecture by Rita Singh: Hidden Markov Modeling (3) (PDF - 1.4 MB)
916
17
Segment-Based ASR (PDF)
Guest Lecture by Lee Hetherington: Finite-State Transducers (PDF)
1018
19
Acoustic-Phonetic Modeling (PDF)
Robust ASR (1) (PDF)
1120
21
Guest Lecture by Timothy Hazen: Robust ASR (2) (PDF)
Guest Lecture by Timothy Hazen: Adaptation (PDF)
1222
23
Speech Understanding (PDF - 1.1 MB)
Guest Lecture by Timothy Hazen: Paralinguistic Information (PDF - 1.0 MB)
13Quiz 2
No Lecture
14
Term Project Presentations



RealOne™ is a trademark or a registered trademark of RealNetworks, Inc.
QuickTime® is a trademark of Apple Computer, Inc., registered in the U.S. and other countries.
Windows Media® is a registered trademark or trademark of Microsoft Corporation in the U.S. and/or other countries.


 



 








© 2017 Coursepedia.com, by Higher Ed Media LLC. All Rights Reserved.