An efficient, fast matching approach using posterior probability estimates in speech recognition

Sherif Abdou, Michael S Scordilis

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

1 Citation (Scopus)

Abstract

Acoustic fast matching is an effective technique to accelerate the search process in large vocabulary continuous speech recognition. This paper introduces a novel fast matching method. This method is based on the evaluation of future posterior probabilities for a look-ahead number of timeframes in order to exclude unlikely phone models as early as possible during the search. In contrast to the likelihood scores used by more traditional fast matching methods these posterior probabilities are more discriminative by nature as they sum up to unity over all the possible models. By applying the proposed method we managed to reduce by 66% the decoding time consumed in our timesynchronous Viterbi decoder for a recognition task based on the Wall Street Journal database with virtually no additional decoding errors.

Original languageEnglish (US)
Title of host publicationEUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology
PublisherInternational Speech Communication Association
Pages1161-1164
Number of pages4
StatePublished - 2003
Event8th European Conference on Speech Communication and Technology, EUROSPEECH 2003 - Geneva, Switzerland
Duration: Sep 1 2003Sep 4 2003

Other

Other8th European Conference on Speech Communication and Technology, EUROSPEECH 2003
CountrySwitzerland
CityGeneva
Period9/1/039/4/03

Fingerprint

Speech recognition
Decoding
Continuous speech recognition
Acoustics
acoustics
vocabulary
evaluation

ASJC Scopus subject areas

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

Cite this

Abdou, S., & Scordilis, M. S. (2003). An efficient, fast matching approach using posterior probability estimates in speech recognition. In EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology (pp. 1161-1164). International Speech Communication Association.

An efficient, fast matching approach using posterior probability estimates in speech recognition. / Abdou, Sherif; Scordilis, Michael S.

EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology. International Speech Communication Association, 2003. p. 1161-1164.

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

Abdou, S & Scordilis, MS 2003, An efficient, fast matching approach using posterior probability estimates in speech recognition. in EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology. International Speech Communication Association, pp. 1161-1164, 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, Geneva, Switzerland, 9/1/03.
Abdou S, Scordilis MS. An efficient, fast matching approach using posterior probability estimates in speech recognition. In EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology. International Speech Communication Association. 2003. p. 1161-1164
Abdou, Sherif ; Scordilis, Michael S. / An efficient, fast matching approach using posterior probability estimates in speech recognition. EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology. International Speech Communication Association, 2003. pp. 1161-1164
@inproceedings{961b34c9ccc9462faba15029afefc49d,
title = "An efficient, fast matching approach using posterior probability estimates in speech recognition",
abstract = "Acoustic fast matching is an effective technique to accelerate the search process in large vocabulary continuous speech recognition. This paper introduces a novel fast matching method. This method is based on the evaluation of future posterior probabilities for a look-ahead number of timeframes in order to exclude unlikely phone models as early as possible during the search. In contrast to the likelihood scores used by more traditional fast matching methods these posterior probabilities are more discriminative by nature as they sum up to unity over all the possible models. By applying the proposed method we managed to reduce by 66{\%} the decoding time consumed in our timesynchronous Viterbi decoder for a recognition task based on the Wall Street Journal database with virtually no additional decoding errors.",
author = "Sherif Abdou and Scordilis, {Michael S}",
year = "2003",
language = "English (US)",
pages = "1161--1164",
booktitle = "EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology",
publisher = "International Speech Communication Association",

}

TY - GEN

T1 - An efficient, fast matching approach using posterior probability estimates in speech recognition

AU - Abdou, Sherif

AU - Scordilis, Michael S

PY - 2003

Y1 - 2003

N2 - Acoustic fast matching is an effective technique to accelerate the search process in large vocabulary continuous speech recognition. This paper introduces a novel fast matching method. This method is based on the evaluation of future posterior probabilities for a look-ahead number of timeframes in order to exclude unlikely phone models as early as possible during the search. In contrast to the likelihood scores used by more traditional fast matching methods these posterior probabilities are more discriminative by nature as they sum up to unity over all the possible models. By applying the proposed method we managed to reduce by 66% the decoding time consumed in our timesynchronous Viterbi decoder for a recognition task based on the Wall Street Journal database with virtually no additional decoding errors.

AB - Acoustic fast matching is an effective technique to accelerate the search process in large vocabulary continuous speech recognition. This paper introduces a novel fast matching method. This method is based on the evaluation of future posterior probabilities for a look-ahead number of timeframes in order to exclude unlikely phone models as early as possible during the search. In contrast to the likelihood scores used by more traditional fast matching methods these posterior probabilities are more discriminative by nature as they sum up to unity over all the possible models. By applying the proposed method we managed to reduce by 66% the decoding time consumed in our timesynchronous Viterbi decoder for a recognition task based on the Wall Street Journal database with virtually no additional decoding errors.

UR - http://www.scopus.com/inward/record.url?scp=85009165892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009165892&partnerID=8YFLogxK

M3 - Conference contribution

SP - 1161

EP - 1164

BT - EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology

PB - International Speech Communication Association

ER -