Lexical access in connected speech recognition

Authors:
Ted Briscoe
Affiliations:
University of Cambridge, Cambridge, UK
Venue:
ACL '89 Proceedings of the 27th annual meeting on Association for Computational Linguistics
Year:
1989

Citing 6
Cited 1

Computational lexicography for natural language processing

Computational lexicography for natural language processing
LDOCE and speech recognition

Computational lexicography for natural language processing
Exploiting Sequential Phonetic Constraints in Recognizing Spoken Words

Exploiting Sequential Phonetic Constraints in Recognizing Spoken Words
A multi-purpose interface to an on-line dictionary

EACL '87 Proceedings of the third conference on European chapter of the Association for Computational Linguistics
The role of phonology in speech processing

COLING '86 Proceedings of the 11th coference on Computational linguistics
Word boundary identification from phoneme sequence constraints in automatic continuous speech recognition

COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 1

A cost-benefit analysis of hybrid phone-manner representations for ASR

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses two issues concerning lexical access in connected speech recognition: 1) the nature of the pre-lexical representation used to initiate lexical lookup 2) the points at which lexical look-up is triggered off this representation. The results of an experiment are reported which was designed to evaluate a number of access strategies proposed in the literature in conjunction with several plausible pre-lexical representations of the speech input. The experiment also extends previous work by utilising a dictionary database containing a realistic rather than illustrative English vocabulary.