Discriminative training of hierarchical acoustic models for large vocabulary continuous speech recognition
In this paper we propose discriminative training of hierarchical acoustic models for large vocabulary continuous speech recognition tasks. After presenting our hierarchical modeling framework, we describe how the models can be generated with either minimum classification error or large-margin traini...
Main Authors: | Chang, Hung-An, Glass, James R. |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | en_US |
Published: |
Institute of Electrical and Electronics Engineers
2011
|
Online Access: | http://hdl.handle.net/1721.1/60562 https://orcid.org/0000-0002-3097-360X |
Similar Items
-
Large vocabulary continuous speech recognition using linguistic features and constraints
by: Tang, Min, Ph. D. Massachusetts Institute of Technology
Published: (2006) -
Acoustic-phonetic constraints in continuous speech recognition: a case study using the digit vocabulary.
by: Chen, Francine Robina.
Published: (2005) -
Finding acoustic regularities in speech : applications to phonetic recognition
by: Glass, James Robert
Published: (2005) -
Artificial context-dependent acoustic modelling for large vocabulary continous speech reorganition /
by: Abdul Manan Ahmad, author, et al.
Published: (2008) -
Reliability-Based Large-Vocabulary Audio-Visual Speech Recognition
by: Wentao Yu, et al.
Published: (2022-07-01)