A Cost-Benefit Analysis of Hybrid Phone-Manner Representations for ASR

Abstract

In the past decade, several researchers have started reinvestigating the use of sub-phonetic models for lexical representations within automatic speech recognition systems. Lest history repeat itself, it may be instructive to mine the further past for models of lexical representations in the lexical access literature. In this work, we re-evaluate the model… (More)

Topics

4 Figures and Tables

Cite this paper

@inproceedings{FoslerLussier2005ACA, title={A Cost-Benefit Analysis of Hybrid Phone-Manner Representations for ASR}, author={Eric Fosler-Lussier and C. Anton Rytting}, booktitle={HLT/EMNLP}, year={2005} }