Home

academics

HST 728
Automatic Speech Recognition

Term: Spring

Course Director(s): James R. Glass
Time:
TBD
Location:
TBD
Course Website:
None
Prerequisite:
6.011 and 6.036
Restrictions:
None
MIT Units:
3-1-8 (G-Level Credit)
Harvard Units:
Unknown
Introduces the rapidly developing fields of automatic speech recognition and spoken language processing. Topics include acoustic theory of speech production, acoustic-phonetics, signal representation, acoustic and language modeling, search, hidden Markov modeling, neural networks models, adaptation, and other related speech processing topics. Lecture material intersperses theory with practice. Includes problem sets, laboratory exercises, and opened-ended term project.