Using finite state models for the integration of hierarchical LMs into ASR systems

Authors:
Raquel Justo;M. Inés Torres
Affiliations:
University of the Basque Country, Leioa, Spain;University of the Basque Country, Leioa, Spain
Venue:
MCPR'11 Proceedings of the Third Mexican conference on Pattern recognition
Year:
2011

Citing 5
Cited 0

Inference of k-Testable Languages in the Strict Sense and Application to Syntactic Pattern Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimation of stochastic context-free grammars and their use as language models

Computer Speech and Language
Phrase classes in two-level language models for ASR

Pattern Analysis & Applications
Impact of the approaches involved on word-graph derivation from the ASR system

IbPRIA'11 Proceedings of the 5th Iberian conference on Pattern recognition and image analysis
A specialized on-the-fly algorithm for lexicon and language model composition

IEEE Transactions on Audio, Speech, and Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Through out this work we explore different methods to integrate a complex Language Model (a hierarchical Language Model based on classes of phrases) into an Automatic Speech Recognition (ASR) system. The integration is carried out by means of a composition of the different Stochastic Finite State Automata associated to the specific Language Model. This method is based on the same idea employed to integrate the different knowledge sources involved in the recognition process when a classical word-based Language Model is considered. The obtained results show that this integrated architecture provides better ASR system performance than a two-pass decoder where the complex LM is employed to reorder the N-best list.