Title:    Adaptation /Normalization   (Lecture)

Time: Friday, March 19, 1:00 PM - 3:00 PM

Location:    Tucson 5

Chair: Chin Lee    (Bell Labs, Lucent Technologies)

1:00 PM    SP-24.1
Fast Speaker Adaptation Using a priori Knowledge
Roland Kuhn (Speech Technology Laboratory, Panasonic Technologies Inc.), Patrick Nguyen (Institut Eurecom), Jean-Claude Junqua, Robert C Boman, Nancy A Niedzielski, Steven C Fincke, Kenneth L Field, Matteo Contolini (Speech Technology Laboratory, Panasonic Technologies Inc.)
[abstract]  [manuscript]

1:15 PM SP-24.2
Speaker Adaptation Uing Maximum Likelihood Model Interpolation
Zuoying Wang (EE. Department, Tshinghua Univ., Beijing, China), Feng Liu (Electronic Engineering Department, Tsinghua Univ., Beijing, China)
[abstract]  [manuscript]

1:30 PM SP-24.3
Speaker Adaptation with All-Pass Transforms
John W McDonough, William J Byrne (Center for Language and Speech Processing, The Johns Hopkins University)
[abstract]  [manuscript]

1:45 PM SP-24.4
Improved Methods for Vocal Tract Normalization
Lutz Welling, Stephan Kanthak, Hermann Ney (RWTH Aachen - University of Technology)
[abstract]  [manuscript]

2:00 PM SP-24.5
Rapid Speech Recognizer Adaptation to New Speakers
Vassilis Digalakis (Technical U. of Crete), Sid Berkowitz (Department of Defense), Enrico Bocchieri (AT&T), Costas Boulis (Technical U. of Crete), William Byrne (Johns Hopkins U.), Heather Collier (West Virginia U.), Adrian Corduneanu (U. of Toronto), Ashvin Kannan (Nuance Communications), Sanjeev Khudanpur (Johns Hopkins U.), Ananth Sankar (SRI)
[abstract]  [manuscript]

2:15 PM SP-24.6
Tree-Structured Models of Parameter Dependence for Rapid Adaptation in Large Vocabulary Conversational Speech Recognition
Ashvin Kannan (Nuance Communications), Sanjeev P Khudanpur (Johns Hopkins University)
[abstract]  [manuscript]

2:30 PM SP-24.7
Correlation Modeling Of MLLR Transform Biases For Rapid HMM Adaptation To New Speakers
Enrico L Bocchieri (AT&T Research), Vassilis Digalakis (Technical University Of Crete), Adrian Corduneanu (University Of Toronto), Costas Boulis (Technical University Of Crete)
[abstract]  [manuscript]

2:45 PM SP-24.8
Speech Recognition in a Reverberant Environment using Matched Filter Array (MFA) Processing and Linguistic-Tree Maximum Likelihood Linear Regression (LT-MLLR) Adaptation.
Prabhu Raghavan, Richard J Renomeron, Chiwei Che, Dong-Suk Yuk, James L Flanagan (CAIP Center, Rutgers University, Piscataway, NJ 08854)
[abstract]  [manuscript]

< SP-23 SP-25 >

Last Update: February 4, 1999 Ingo Höntsch