Spoken Language Technologies
Explore the theory and practice that underlies modern automatic speech recognition (ASR) systems and related spoken language technologies. Discuss the acoustic theory of speech production, digital signal processing for speech signals, Hidden Markov Models, Gaussian Mixture Models, language models, finite state transducers, decoding algorithms, and deep neural networks. Computer Science 381S and 395T (Topic: Spoken Language Technologies) may not both be counted. Three lecture hours a week for one semester.
Prerequisites & course information
Explore the theory and practice that underlies modern automatic speech recognition (ASR) systems and related spoken language technologies. Discuss the acoustic theory of speech production, digital signal processing for speech signals, Hidden Markov Models, Gaussian Mixture Models, language models, finite state transducers, decoding algorithms, and deep neural networks. Computer Science 381S and 395T (Topic: Spoken Language Technologies) may not both be counted. Three lecture hours a week for one semester.
Sources
- Course catalogue ↗2026-2027