Searching for authors named "Karen Livescu" – sorted by Relevance.
15 documents found, showing 1 through 10.
Next 10 →
-
Feature-based Pronunciation Modeling with Trainable Asynchrony Probabilities
- …Feature-based Pronunciation Modeling with Trainable Asynchrony Probabilities Karen Livescu…
- Cited by 11 (6 self) – Add To MetaCart
-
Segment-Based Recognition on the PhoneBook Task: Initial Results and Observations on Duration Modeling
- … and Ocean Surveillance Center. Karen Livescu and James Glass Spoken Language Systems Group MIT Laboratory…
- Cited by 5 (2 self) – Add To MetaCart
-
An asynchronous DBN for audio-visual speech recognition
- …AN ASYNCHRONOUS DBN FOR AUDIO-VISUAL SPEECH RECOGNITION Kate Saenko and Karen Livescu Computer…
- Cited by 1 (1 self) – Add To MetaCart
-
Lexical Modeling Of Non-Native Speech For Automatic Speech Recognition
- …1 LEXICAL MODELING OF NON-NATIVE SPEECH FOR AUTOMATIC SPEECH RECOGNITION Karen Livescu and James…
- Cited by 17 (0 self) – Add To MetaCart
-
Hidden feature models for speech recognition using dynamic Bayesian networks
- …Hidden Feature Models for Speech Recognition Using Dynamic Bayesian Networks Karen Livescu, James…
- Cited by 24 (4 self) – Add To MetaCart
-
Feature-based Pronunciation Modeling for Speech Recognition
- …Feature-based Pronunciation Modeling for Speech Recognition Karen Livescu and James Glass MIT…
- Add To MetaCart
-
Audiovisual speech recognition with articulator positions as hidden variables
- …-Johnson, Karen Livescu, Partha Lal and Kate Saenko ∗ University of Illinois at Urbana-Champaign, MIT, University…
- Cited by 1 (1 self) – Add To MetaCart
-
Production domain modeling of pronunciation for visual speech recognition
- …PRODUCTION DOMAIN MODELING OF PRONUNCIATION FOR VISUAL SPEECH RECOGNITION Kate Saenko, Karen…
- Cited by 2 (2 self) – Add To MetaCart
-
Articulatory feature classifiers trained on 2000 hours of telephone speech
- …,2 , Mathew Magimai-Doss 2 , Simon King 1 , Karen Livescu 3 , Özgür Çetin 2 . Abstract This paper is intended…
- Cited by 3 (2 self) – Add To MetaCart
-
Visual speech recognition with loosely synchronized feature streams
- …Visual Speech Recognition with Loosely Synchronized Feature Streams Kate Saenko, Karen Livescu…
- Cited by 8 (4 self) – Add To MetaCart
Showing 1 through 10.
Next 10 →
