Integrating multiple knowledge sources for improved speech understanding

Sherif Abdou, Michael S Scordilis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In spoken dialog systems it is often the case that the sentence produced by the decoder with the highest recognition probability may not be the best choice for extracting the intended concepts. Lower ranking hypotheses may present better alternatives. In this paper, we show how to integrate multiple knowledge sources for the decision of selecting one of these hypotheses. A scoring schema combining information from the recognizer output, the parser, an utterance type classifier and dialog context is used. The scaling weights of the combined scores are determined automatically by an optimization procedure. Finally, we show the results of testing this approach and its performance compared to the approach of selecting the best recognition hypothesis.

Original languageEnglish (US)
Title of host publicationEUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology
PublisherInternational Speech Communication Association
Pages1783-1786
Number of pages4
ISBN (Electronic)8790834100, 9788790834104
StatePublished - 2001
Event7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001 - Aalborg, Denmark
Duration: Sep 3 2001Sep 7 2001

Other

Other7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001
CountryDenmark
CityAalborg
Period9/3/019/7/01

Fingerprint

Classifiers
Testing
knowledge
scaling
ranking
communication technology
dialogue
performance

ASJC Scopus subject areas

  • Communication
  • Linguistics and Language
  • Computer Science Applications
  • Software

Cite this

Abdou, S., & Scordilis, M. S. (2001). Integrating multiple knowledge sources for improved speech understanding. In EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology (pp. 1783-1786). International Speech Communication Association.

Integrating multiple knowledge sources for improved speech understanding. / Abdou, Sherif; Scordilis, Michael S.

EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, 2001. p. 1783-1786.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abdou, S & Scordilis, MS 2001, Integrating multiple knowledge sources for improved speech understanding. in EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, pp. 1783-1786, 7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001, Aalborg, Denmark, 9/3/01.
Abdou S, Scordilis MS. Integrating multiple knowledge sources for improved speech understanding. In EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association. 2001. p. 1783-1786
Abdou, Sherif ; Scordilis, Michael S. / Integrating multiple knowledge sources for improved speech understanding. EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, 2001. pp. 1783-1786
@inproceedings{11f0054b06814f418a2dfece93c75d03,
title = "Integrating multiple knowledge sources for improved speech understanding",
abstract = "In spoken dialog systems it is often the case that the sentence produced by the decoder with the highest recognition probability may not be the best choice for extracting the intended concepts. Lower ranking hypotheses may present better alternatives. In this paper, we show how to integrate multiple knowledge sources for the decision of selecting one of these hypotheses. A scoring schema combining information from the recognizer output, the parser, an utterance type classifier and dialog context is used. The scaling weights of the combined scores are determined automatically by an optimization procedure. Finally, we show the results of testing this approach and its performance compared to the approach of selecting the best recognition hypothesis.",
author = "Sherif Abdou and Scordilis, {Michael S}",
year = "2001",
language = "English (US)",
pages = "1783--1786",
booktitle = "EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology",
publisher = "International Speech Communication Association",

}

TY - GEN

T1 - Integrating multiple knowledge sources for improved speech understanding

AU - Abdou, Sherif

AU - Scordilis, Michael S

PY - 2001

Y1 - 2001

N2 - In spoken dialog systems it is often the case that the sentence produced by the decoder with the highest recognition probability may not be the best choice for extracting the intended concepts. Lower ranking hypotheses may present better alternatives. In this paper, we show how to integrate multiple knowledge sources for the decision of selecting one of these hypotheses. A scoring schema combining information from the recognizer output, the parser, an utterance type classifier and dialog context is used. The scaling weights of the combined scores are determined automatically by an optimization procedure. Finally, we show the results of testing this approach and its performance compared to the approach of selecting the best recognition hypothesis.

AB - In spoken dialog systems it is often the case that the sentence produced by the decoder with the highest recognition probability may not be the best choice for extracting the intended concepts. Lower ranking hypotheses may present better alternatives. In this paper, we show how to integrate multiple knowledge sources for the decision of selecting one of these hypotheses. A scoring schema combining information from the recognizer output, the parser, an utterance type classifier and dialog context is used. The scaling weights of the combined scores are determined automatically by an optimization procedure. Finally, we show the results of testing this approach and its performance compared to the approach of selecting the best recognition hypothesis.

UR - http://www.scopus.com/inward/record.url?scp=32144441480&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=32144441480&partnerID=8YFLogxK

M3 - Conference contribution

SP - 1783

EP - 1786

BT - EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

PB - International Speech Communication Association

ER -