Integrating natural language constraints into HMM-based speech recognition

Author

Murveit, Hy ; Moore, Robert

Author_Institution

SRI Int., Menlo Park, CA, USA

fYear

1990

fDate

3-6 Apr 1990

Firstpage

573

Abstract

An approach to implementing spoken language systems is discussed. This approach takes full advantage of syntactic and semantic constraints provided by a natural language processing component in the speed understanding task and provides a tractable search space. The results indicate that the approach is a promising one for large-vocabulary spoken language systems. Parse times within a factor of 20 of real time are achieved for high-perplexity syntactic grammars with resulting hidden Markov model recognition computational requirements (2500 active words/frame) that are well within the capability of high-speed multiprocessor computers or special-purpose speech recognition hardware

Keywords

Markov processes; grammars; natural languages; search problems; speech recognition; hidden Markov model; natural language; search space; semantic constraints; speech recognition; speed understanding task; spoken language systems; syntactic constraints; syntactic grammars; Acoustic applications; Error correction; Hardware; Hidden Markov models; Lattices; Natural language processing; Natural languages; Speech processing; Speech recognition; Strontium; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115777

Filename

115777