A stochastic speech understanding method to generate interlingual representations

Koichi Tanigaki, Yoshinori Sagisaka

Research output: Contribution to journalArticle

Abstract

The purpose of this paper is to create an understanding system that can reduce the recognition error that prevents semantic analysis, and that is robust to speech input. A method is proposed in which semantic analysis and speech recognition are integrated on the basis of a statistical model, and the procedure is optimized as a high-level recognition process from speech to semantics. As a method of realizing the idea effectively and efficiently, search of the word graph by means of a decision tree is proposed. Using the proposed method, an identification experiment is performed for the semantics represented by the intermediate language. It is a problem of segmentation of utterances into an average of 1.6 semantic units, and the assignment of the semantic units to 7600 classes characterized by combinations of utterance action and concept. In the speech recognition experiment the understanding error is improved by 8.5% compared to the case in which the 1-best recognition candidate is input.

Original languageEnglish
Pages (from-to)52-62
Number of pages11
JournalSystems and Computers in Japan
Volume33
Issue number3
DOIs
Publication statusPublished - 2002 Mar
Externally publishedYes

Fingerprint

Semantics
Semantic Analysis
Speech Recognition
Speech recognition
Unit
Decision tree
Statistical Model
Experiment
Assignment
Segmentation
Decision trees
Speech
Graph in graph theory
Experiments

Keywords

  • Decision tree
  • Intermediate language
  • Speech understanding
  • Word graph

ASJC Scopus subject areas

  • Hardware and Architecture
  • Information Systems
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

A stochastic speech understanding method to generate interlingual representations. / Tanigaki, Koichi; Sagisaka, Yoshinori.

In: Systems and Computers in Japan, Vol. 33, No. 3, 03.2002, p. 52-62.

Research output: Contribution to journalArticle

@article{2893f4b61fc2426ca25fbe63ff3b19bb,
title = "A stochastic speech understanding method to generate interlingual representations",
abstract = "The purpose of this paper is to create an understanding system that can reduce the recognition error that prevents semantic analysis, and that is robust to speech input. A method is proposed in which semantic analysis and speech recognition are integrated on the basis of a statistical model, and the procedure is optimized as a high-level recognition process from speech to semantics. As a method of realizing the idea effectively and efficiently, search of the word graph by means of a decision tree is proposed. Using the proposed method, an identification experiment is performed for the semantics represented by the intermediate language. It is a problem of segmentation of utterances into an average of 1.6 semantic units, and the assignment of the semantic units to 7600 classes characterized by combinations of utterance action and concept. In the speech recognition experiment the understanding error is improved by 8.5{\%} compared to the case in which the 1-best recognition candidate is input.",
keywords = "Decision tree, Intermediate language, Speech understanding, Word graph",
author = "Koichi Tanigaki and Yoshinori Sagisaka",
year = "2002",
month = "3",
doi = "10.1002/scj.1113",
language = "English",
volume = "33",
pages = "52--62",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "3",

}

TY - JOUR

T1 - A stochastic speech understanding method to generate interlingual representations

AU - Tanigaki, Koichi

AU - Sagisaka, Yoshinori

PY - 2002/3

Y1 - 2002/3

N2 - The purpose of this paper is to create an understanding system that can reduce the recognition error that prevents semantic analysis, and that is robust to speech input. A method is proposed in which semantic analysis and speech recognition are integrated on the basis of a statistical model, and the procedure is optimized as a high-level recognition process from speech to semantics. As a method of realizing the idea effectively and efficiently, search of the word graph by means of a decision tree is proposed. Using the proposed method, an identification experiment is performed for the semantics represented by the intermediate language. It is a problem of segmentation of utterances into an average of 1.6 semantic units, and the assignment of the semantic units to 7600 classes characterized by combinations of utterance action and concept. In the speech recognition experiment the understanding error is improved by 8.5% compared to the case in which the 1-best recognition candidate is input.

AB - The purpose of this paper is to create an understanding system that can reduce the recognition error that prevents semantic analysis, and that is robust to speech input. A method is proposed in which semantic analysis and speech recognition are integrated on the basis of a statistical model, and the procedure is optimized as a high-level recognition process from speech to semantics. As a method of realizing the idea effectively and efficiently, search of the word graph by means of a decision tree is proposed. Using the proposed method, an identification experiment is performed for the semantics represented by the intermediate language. It is a problem of segmentation of utterances into an average of 1.6 semantic units, and the assignment of the semantic units to 7600 classes characterized by combinations of utterance action and concept. In the speech recognition experiment the understanding error is improved by 8.5% compared to the case in which the 1-best recognition candidate is input.

KW - Decision tree

KW - Intermediate language

KW - Speech understanding

KW - Word graph

UR - http://www.scopus.com/inward/record.url?scp=0036500120&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036500120&partnerID=8YFLogxK

U2 - 10.1002/scj.1113

DO - 10.1002/scj.1113

M3 - Article

VL - 33

SP - 52

EP - 62

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 3

ER -