6.345J Automatic Speech Recognition
Introduces the rapidly developing fields of automatic speech recognition and spoken language processing. Topics include acoustic theory of speech production and perception, acoustic-phonetics, signal representation, acoustic and language modeling, search, hidden Markov modeling, robustness, adaptation, discriminative and alternative approaches. Lectures interspersed with theory and applications. Assignments include problems, laboratory exercises, and a term project. 4 Engineering Design Points.
This class counts for a total of 12 credits. This is a graduate-level class.
You can find more information on MIT OpenCourseWare at the Automatic Speech Recognition site.
© Copyright 2015 Yasyf Mohamedali