Title:    Acoustic Modeling I   (Lecture)

Time: Tuesday, March 16, 3:45 PM - 5:45 PM

Location:    Tucson 5

Chair: Wu Chou    (Lucent Technologies Bell Labs)

3:45 PM    SP-4.1
Using a large vocabulary continuous speech recognizer for a constrained domain with limited training
Man-hung Siu, Michael Jonas, Herbert Gish (BBN Technologies/GTE Internetworking)
[abstract]  [manuscript]

4:00 PM SP-4.2
Initial Evaluation of Hidden Dynamic Models on Conversational Speech
Joseph Picone (Institute for Signal and Information Processing, MS State), Sandi Pike (Brown University), Roland Reagan (Carnegie Mellon University), Terri Kamm (Department of Defense), John Bridle (Dragon Systems U.K.), Li Deng, Jeff Ma (University of Waterloo), Hywel Richards (Dragon Systems U.K.), Mike Schuster (ATR)
[abstract]  [manuscript]

4:15 PM SP-4.3
Convolutional Density Estimation in Hidden Markov Models for Speech Recognition
Spyros Matsoukas, George Zavaliagkos (BBN Technologies, GTE Internetworking)
[abstract]  [manuscript]

4:30 PM SP-4.4
AUTOMATIC CLUSTERING AND GENERATION OF CONTEXTUAL QUESTIONS FOR TIED STATES IN HIDDEN MARKOV MODELS
Rita Singh, Bhiksha Raj, Richard M Stern (Carnegie Mellon University)
[abstract]  [manuscript]

4:45 PM SP-4.5
Partly Hidden Markov Model and its Application to Speech Recognition
Tetsunori Kobayashi, Junko Furuyama, Ken Masumitsu (Waseda University)
[abstract]  [manuscript]

5:00 PM SP-4.6
HIDDEN MARKOV MODELS WITH DIVERGENCE BASED VECTOR QUANTIZED VARIANCES
Jae H Kim, Raziel Haimi-Cohen, Frank K Soong (Lucent Technologies)
[abstract]  [manuscript]

5:15 PM SP-4.7
HMM Training Based on Quality Measurement
Yuqing Gao, Ea-Ee Jan, Mukund Padmanabhan, Michael Picheny (IBM T.J. Watson Research Center)
[abstract]  [manuscript]

5:30 PM SP-4.8
Prosodic Word Boundary Detection Using Statistical Modeling of Moraic Fundamental Frequency Contours and Its Use for Continuous Speech Recognition
Koji Iwano, Keikichi Hirose (University of Tokyo)
[abstract]  [manuscript]

< SP-3 SP-5 >

Last Update: February 4, 1999 Ingo Höntsch