Home
About
Advanced Search
Browse by Discipline
Scientific Societies
E-print Alerts
Add E-prints
FAQ
•
HELP
•
SITE MAP
•
CONTACT US
Search
Advanced Search
Livescu, Karen - Toyota Technological Institute at Chicago
6. Ongoing/future work 2. Examples
LANDMARK-BASED SPEECH RECOGNITION: REPORT OF THE 2004 JOHNS HOPKINS SUMMER WORKSHOP
Visual Speech Recognition with Loosely Synchronized Feature Streams Kate Saenko, Karen Livescu, Michael Siracusa, Kevin Wilson, James Glass, and Trevor Darrell
Feature-based Pronunciation Modeling with Trainable Asynchrony Probabilities
AUDIOVISUAL SPEECH RECOGNITION WITH ARTICULATOR POSITIONS AS HIDDEN VARIABLES
Multi-View Learning of Acoustic Features for Speaker Recognition
Domain Adaptation with Unlabeled Data for Dialog Act Tagging Anna Margolis1,2
AN ASYNCHRONOUS DBN FOR AUDIO-VISUAL SPEECH RECOGNITION Kate Saenko and Karen Livescu
Multi-View Clustering via Canonical Correlation Analysis Kamalika Chaudhuri kamalika@soe.ucsd.edu
Feature-Based Pronunciation Modeling for Automatic Speech Recognition
AN ARTICULATORY FEATURE-BASED TANDEM APPROACH AND FACTORED OBSERVATION MODELING
ON THE PHONETIC INFORMATION IN ULTRASONIC MICROPHONE SIGNALS Karen Livescu
PRODUCTION DOMAIN MODELING OF PRONUNCIATION FOR VISUAL SPEECH RECOGNITION
Phonological Models in Automatic Speech Recognition
From Sound to Sense: 50+ Years of Discoveries in Speech Communication June 11 -June 13, 2004 at MIT
