Abstracts for the theses below are available by clicking on the titles. Postscript versions of some theses are available.

Ph.D. Theses

• Colin Wightman, EE Ph.D. 1991,
  Automatic detection of prosodic constituents for parsing

• Vassilios Digalakis, SE Ph.D. 1992,
  Segment-based stochastic models of spectral dynamics for continuous speech recognition

• Nanette Veilleux, SE Ph.D. 1994,
  Computational models of the prosody/syntax mapping for spoken language systems

• Owen Kimball, EE Ph.D. 1994,
  Segment modeling alternatives for continuous speech recognition

• Ken Ross, EE Ph.D. 1995,
  Modeling of intonation for speech synthesis

• Orith Ronen, BME Ph.D. 1996,
  Dependence tree models of intra-utterance phone dependence

• Ashvin Kannan, EE Ph.D. 1997,
  Adaptation of spectral trajectory models for large vocabulary continuous speech recognition

• Rukmini Iyer, EE Ph.D. 1998,
  Improving and predicting performance of statistical language models in sparse domains

• Man-Hung Siu, EE Ph.D. 1998,
  Learning local lexical structure in spontaneous speech language modeling

• Michiel Bacchiani, EE Ph.D. 1999,
  Speech Recognition System Design Based on Automatically Derived Units

M.S. Theses

• John Butzberger, Jr., M.S. EE 1989,
  Statistical methods for intonation pattern recognition

• Ibrahim Bechwati, M.S. EE 1990,
  Structural alternatives in stochastic segment modeling for speech recognition

• Burhan Necioglu, M.S. EE 1992,
  Bayesian adaptation of the stochastic segment model for speech recognition

• Ashvin Kannan, M.S. EE 1992,
  Robust estimation of stochastic segment models for word recognition

• Cynthia Fong, M.S. EE 1993,
  Statistical models of duration for synthesis and recognition

• Rukmini Iyer, M.S. EE 1994,
  Language modeling with sentence-level mixtures

• Fred Richardson, M.S. EE 1995,
  Search algorithms for speech recognition

• Rebecca Bates, M.S. EE 1996,
  Reducing the effects of linear channel distortion on continuous speech recognition

• Cameron Fordyce, M.S. EE 1998,
  Control of prosodic patterns for speech generation in human-computer dialogs

• Yuliya Lobacheva, M.S. EE 2000,
  Discourse Mixture Language Modeling