Discriminative training of hierarchical acoustic models for large vocabulary continuous speech recognition
Name
Glass_Discriminative training.pdf
Size
112.92 KB
Format
Adobe PDF
Checksum (MD5)
5011c8964c446dcd4ca0839c5954b704
Author(s)
Chang, Hung-An
Glass, James R.
Date Issued
May 2009
Journal
IEEE International Conference on Acoustics, Speech and Signal Processing, 2009. ICASSP 2009.
Publisher
Institute of Electrical and Electronics Engineers
Citation
Hung-An Chang, and J.R. Glass. “Discriminative training of hierarchical acoustic models for large vocabulary continuous speech recognition.” Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on. 2009. 4481-4484. © Copyright 2009 IEEE
Version
Final published version
Abstract
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 training. Experiments on a large vocabulary lecture transcription task show that the hierarchical model can yield more than 1.0% absolute word error rate reduction over non-hierarchical models for both kinds of discriminative training.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/ICASSP.2009.4960625
