Full expansion of context-dependent networks in large vocabulary speech recognition

We combine our earlier approach to context-dependent network representation with our algorithm for determining weighted networks to build optimized networks for large-vocabulary speech recognition combining an n-gram language model, a pronunciation dictionary and context-dependency modeling. While f...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohri, M., Riley, M., Hindle, D., Ljolje, A., Pereira, F.
Format: Conference Proceeding
Language:English
Subjects:
Acoustic transducers
Business communication
Context modeling
Dictionaries
Intelligent networks
Natural languages
Runtime
Speech recognition
Viterbi algorithm
Vocabulary
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We combine our earlier approach to context-dependent network representation with our algorithm for determining weighted networks to build optimized networks for large-vocabulary speech recognition combining an n-gram language model, a pronunciation dictionary and context-dependency modeling. While fully-expanded networks have been used before in restrictive settings (medium vocabulary or no cross-word contexts), we demonstrate that our network determination method makes it practical to use fully-expanded networks also in large-vocabulary recognition with full cross-word context modeling. For the DARPA North American Business News task (NAB), we give network sizes and recognition speeds and accuracies using bigram and trigram grammars with vocabulary sizes ranging from 10000 to 160000 words. With our construction, the fully-expanded NAB context-dependent networks contain only about twice as many arcs as the corresponding language models. Interestingly, we also find that, with these networks, real-time word accuracy is improved by increasing the vocabulary size and n-gram order.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.1998.675352