Speech Recognition

Catalog description

This course covers the theory and practice of automatic speech recognition (ASR), with a focus on the statistical approaches that comprise state of the art. The course introduces the overall framework for speech recognition, including speech signal analysis, acoustic modeling using hidden Markov models, language modeling and recognition search. Advanced topics covered will include speaker adaptation, robust speech recognition and speaker identification. The practical side of the course will involve the development of a speech recognition system using a speech recognition software toolkit. Three credits; two-hour lecture and two-hour laboratory. Prerequisites: AI 260 and ENGR 251