A New Approach of Parsing and Search Based on the Divide and Conquer Strategy for Continuous Speech Recognition
Summary :
In this paper, we report a new approach about parsing and searching problem for a given phonetic lattice. The approach is based on the Divide and Conquer (DC) strategy. By dividing the phonetic lattice, we first construct a PD-tree to represent this lattice, then, we parse through this PD-tree to identify the possible sentence which is supposed to be the speech utterance. Next, we propose a new search scheme called Downward Request (DR) search model to decrease the computation costs, and this search model gives us the optimal or N-best solutions. Experiments performed on Chinese speech recognition show us the good results.
- Publication
- IEICE TRANSACTIONS on Information Vol.E78-D No.4 pp.455-465
- Publication Date
- 1995/04/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- PAPER
- Category
- Speech Processing and Acoustics
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
Ming-Sheng WANG, Satoshi IMAI, "A New Approach of Parsing and Search Based on the Divide and Conquer Strategy for Continuous Speech Recognition" in IEICE TRANSACTIONS on Information,
vol. E78-D, no. 4, pp. 455-465, April 1995, doi: .
Abstract: In this paper, we report a new approach about parsing and searching problem for a given phonetic lattice. The approach is based on the Divide and Conquer (DC) strategy. By dividing the phonetic lattice, we first construct a PD-tree to represent this lattice, then, we parse through this PD-tree to identify the possible sentence which is supposed to be the speech utterance. Next, we propose a new search scheme called Downward Request (DR) search model to decrease the computation costs, and this search model gives us the optimal or N-best solutions. Experiments performed on Chinese speech recognition show us the good results.
URL: https://global.ieice.org/en_transactions/information/10.1587/e78-d_4_455/_p
Copy
@ARTICLE{e78-d_4_455,
author={Ming-Sheng WANG, Satoshi IMAI, },
journal={IEICE TRANSACTIONS on Information},
title={A New Approach of Parsing and Search Based on the Divide and Conquer Strategy for Continuous Speech Recognition},
year={1995},
volume={E78-D},
number={4},
pages={455-465},
abstract={In this paper, we report a new approach about parsing and searching problem for a given phonetic lattice. The approach is based on the Divide and Conquer (DC) strategy. By dividing the phonetic lattice, we first construct a PD-tree to represent this lattice, then, we parse through this PD-tree to identify the possible sentence which is supposed to be the speech utterance. Next, we propose a new search scheme called Downward Request (DR) search model to decrease the computation costs, and this search model gives us the optimal or N-best solutions. Experiments performed on Chinese speech recognition show us the good results.},
keywords={},
doi={},
ISSN={},
month={April},}
Copy
TY - JOUR
TI - A New Approach of Parsing and Search Based on the Divide and Conquer Strategy for Continuous Speech Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 455
EP - 465
AU - Ming-Sheng WANG
AU - Satoshi IMAI
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E78-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 1995
AB - In this paper, we report a new approach about parsing and searching problem for a given phonetic lattice. The approach is based on the Divide and Conquer (DC) strategy. By dividing the phonetic lattice, we first construct a PD-tree to represent this lattice, then, we parse through this PD-tree to identify the possible sentence which is supposed to be the speech utterance. Next, we propose a new search scheme called Downward Request (DR) search model to decrease the computation costs, and this search model gives us the optimal or N-best solutions. Experiments performed on Chinese speech recognition show us the good results.
ER -
English
