6.345
Automatic Speech Recognition
Spring 2003
Topics
- Course Overview Acoustic Theory of Speech Production
- Speech Sounds Speech Sounds (continued)
- Signal Representation Vector Quantization
- Pattern Classification (1) Pattern Classification (2)
- Search Hidden Markov Modeling (1)
- Language Modeling Language Modeling (continued)
- Hidden Markov Modeling (2) Hidden Markov Modeling (3)
- Segment-Based ASR Finite-State Transducers
- Acoustic-Phonetic Modeling Robust ASR (1)
- Robust ASR (2) Adaptation
- Speech Understanding Paralinguistic Information
Readings
- Huang, Acero, and Hon. Spoken Language Processing . Upper Saddle River, NJ: Prentice-Hall, 2001. ISBN: 0130226165.
- Jelinek. Statistical Methods for Speech Recognition . Cambridge, MA: MIT Press, 1998. ISBN: 0262100665.
- Rabiner & Juang. Fundamentals of Speech Recognition . Upper Saddle River, NJ: Prentice-Hall, 1993. ISBN: 0130151572.
- Duda, Hart, and Stork. Pattern Classification . New York, NY: Wiley & Sons, 2000. ISBN: 0471056693.
- Stevens. Acoustic Phonetics . MIT Press, 1998. ISBN: 0262692503.
Sources
- Course catalogue ↗Historical OpenCourseWare
- MIT OCW calendar ↗
- MIT OCW syllabus ↗
- Historical MIT OpenCourseWare offering. Named reading entries and schedule topics are automatically extracted from the linked source pages.