Incorporating LR parsing into SPHINX

Published 1 January 1991

Kenji Kita, Wayne Ward

DOI10.1109/icassp.1991.150329

Citations12

TL;DR

The integration of an LR natural language parser with the SPHINX speech recognition system is described and a solution to this problem that involves combining a context-free grammar with a bigram grammar is proposed.

Abstract

The integration of an LR natural language parser with the SPHINX speech recognition system is described. LR parsing was incorporated into SPHINX to provide more global grammatical constraints. However, when using a tight grammar in a left-to-right continuous speech recognizer, when one word is missing or wrong, often several subsequent words are also incorrect. A solution to this problem that involves combining a context-free grammar with a bigram grammar is proposed.>

Keywords

Computer Science

IEEE Transactions on Pattern Analysis and Machine IntelligenceA Maximum Likelihood Approach to Continuous Speech Recognition

1,220 Citations1983L.R. Bahl, Frederick Jelinek +1 more

This paper describes a number of statistical models for use in speech recognition, with special attention to determining the parameters for such models from sparse data, and describes two decoding methods appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks.

Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems

410 Citations2013Masaru Tomita

A Parsing Table Constructor for Nishida and Doshita's System, with examples of left-to-Right on-Line Parsing and Interactive/Personal Machine Translation.

View PDF

Efficient Parsing for Natural Language

403 Citations1986Masaru Tomita

International Conference on Acoustics, Speech, and Signal ProcessingHMM continuous speech recognition using predictive LR parsing

60 Citations2003Kenji Kita, Takeshi Kawabata +1 more

A continuous-speech recognition method that uses an accurate and efficient parsing mechanism, an LR parser, and drives HMM (hidden Markov model) modules directly without any intervening structures such as a phoneme lattice is proposed.

Dynamic programming speech recognition using a context-free grammar

33 Citations2005Hermann Ney

A dynamic programming algorithm for recognizing and parsing spoken word strings of a context-free grammar that can be viewed as a probabilistic extension of the CYK algorithm along with the incorporation of the nonlineer time alignment is presented.

International Conference on Acoustics, Speech, and Signal ProcessingIntegrating natural language constraints into HMM-based speech recognition

23 Citations2002Hy Murveit, Robert T. Moore

An approach to implementing spoken language systems that 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 is discussed.

Improvement of word recognition results by trigram model

17 Citations2005Kiyohiro Shikano

This trigram model is efficiently applied to improve word recognition results using a dynamic programming technique and probabilities of special word sequences are extracted from the Brown Corpus Text Database and these probabilities are also integrated in the dynamic programming algorithm.