A preference-first language processor integrating the unification grammar and Markov language model for speech recognition applications

Authors:
Lee-Feng Chien;K. J. Chen;Lin-Shan Lee
Affiliations:
The Institute of Information Science, Academia Sinica, Taipei, Taiwan, Rep. of China;The Institute of Information Science, Academia Sinica, Taipei, Taiwan, Rep. of China;National Taiwan University, Taipei, Taiwan, Rep. of China
Venue:
ACL '91 Proceedings of the 29th annual meeting on Association for Computational Linguistics
Year:
1991

Citing 4
Cited 0

Natural Language Modeling for Phoneme-to-Text Transcription

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Mandarin Dictation Machine Based Upon a Hierarchical Recognition Approach and Chinese Natural Language Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
An augmented chart data structure with efficient word lattice parsing scheme in speech recognition applications

Speech Communication
Parsing spoken language: a semantic caseframe approach

COLING '86 Proceedings of the 11th coference on Computational linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

A language processor is to find out a most promising sentence hypothesis for a given word lattice obtained from acoustic signal recognition. In this paper a new language processor is proposed, in which unification grammar and Markov language model are integrated in a word lattice parsing algorithm based on an augmented chart, and the island-driven parsing concept is combined with various preference-first parsing strategies defined by different construction principles and decision rules. Test results show that significant improvements in both correct rate of recognition and computation speed can be achieved.