An Efficient One-Pass Search Algorithm for Parsing Spoken Language
Summary :
Spoken language systems such as speech-to-speech dialog translation systems have been gaining more attention in recent years. These systems require full integration of speech recognition and natural language understanding. This paper presents an efficient parsing algorithm that integrates the search problems of speech processing and language processing. The parsing algorithm we propose here is regarded as an extension of the finite-state-network directed, one-pass search algorithm to one directed by a context-free grammar with retention of the time-synchronous procedure. The extended search algorithm is used to find approximately globally optimal sentence hypotheses; it does not have overhead which exists in, for example, hierarchical systems based on the lattice parsing approach. The computational complexity of this search algorithm is proportional to the length of the input speech. As the search process in the speech recognition can directly take account of the predictive information in the sentence parsing, this framework can be extended to sopken language systems which deal with dynamically varying constraints in dialogue situations.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E75-A No.7 pp.944-953
- Publication Date
- 1992/07/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- PAPER
- Category
- Speech
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Michio OKADA, "An Efficient One-Pass Search Algorithm for Parsing Spoken Language" in IEICE TRANSACTIONS on Fundamentals,
vol. E75-A, no. 7, pp. 944-953, July 1992, doi: .
Abstract: Spoken language systems such as speech-to-speech dialog translation systems have been gaining more attention in recent years. These systems require full integration of speech recognition and natural language understanding. This paper presents an efficient parsing algorithm that integrates the search problems of speech processing and language processing. The parsing algorithm we propose here is regarded as an extension of the finite-state-network directed, one-pass search algorithm to one directed by a context-free grammar with retention of the time-synchronous procedure. The extended search algorithm is used to find approximately globally optimal sentence hypotheses; it does not have overhead which exists in, for example, hierarchical systems based on the lattice parsing approach. The computational complexity of this search algorithm is proportional to the length of the input speech. As the search process in the speech recognition can directly take account of the predictive information in the sentence parsing, this framework can be extended to sopken language systems which deal with dynamically varying constraints in dialogue situations.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e75-a_7_944/_p
Copy
@ARTICLE{e75-a_7_944,
author={Michio OKADA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={An Efficient One-Pass Search Algorithm for Parsing Spoken Language},
year={1992},
volume={E75-A},
number={7},
pages={944-953},
abstract={Spoken language systems such as speech-to-speech dialog translation systems have been gaining more attention in recent years. These systems require full integration of speech recognition and natural language understanding. This paper presents an efficient parsing algorithm that integrates the search problems of speech processing and language processing. The parsing algorithm we propose here is regarded as an extension of the finite-state-network directed, one-pass search algorithm to one directed by a context-free grammar with retention of the time-synchronous procedure. The extended search algorithm is used to find approximately globally optimal sentence hypotheses; it does not have overhead which exists in, for example, hierarchical systems based on the lattice parsing approach. The computational complexity of this search algorithm is proportional to the length of the input speech. As the search process in the speech recognition can directly take account of the predictive information in the sentence parsing, this framework can be extended to sopken language systems which deal with dynamically varying constraints in dialogue situations.},
keywords={},
doi={},
ISSN={},
month={July},}
Copy
TY - JOUR
TI - An Efficient One-Pass Search Algorithm for Parsing Spoken Language
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 944
EP - 953
AU - Michio OKADA
PY - 1992
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E75-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 1992
AB - Spoken language systems such as speech-to-speech dialog translation systems have been gaining more attention in recent years. These systems require full integration of speech recognition and natural language understanding. This paper presents an efficient parsing algorithm that integrates the search problems of speech processing and language processing. The parsing algorithm we propose here is regarded as an extension of the finite-state-network directed, one-pass search algorithm to one directed by a context-free grammar with retention of the time-synchronous procedure. The extended search algorithm is used to find approximately globally optimal sentence hypotheses; it does not have overhead which exists in, for example, hierarchical systems based on the lattice parsing approach. The computational complexity of this search algorithm is proportional to the length of the input speech. As the search process in the speech recognition can directly take account of the predictive information in the sentence parsing, this framework can be extended to sopken language systems which deal with dynamically varying constraints in dialogue situations.
ER -
English
