Enhancing phoneme recogniser performance with a simple rule-based language model

Pertti Väyrynen, Johannes Peltola, Tapio Seppänen

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

The phoneme classification inaccuracy at the acoustic phonetic level is a major weakness in most speech recognition systems. However, the inaccuracy will violate phonotactic constraints at the acoustic phonetic level. A better performance is expected if a language model is adopted in a recognition system for post-processing phoneme estimates and making corrections with a set of explicit rules of the language used. We developed a simple language model with a set of rules to correct phoneme classification errors made by a Hidden Markov Model based phoneme recognizer. The experimental results indicate that about 20% of
recognition errors can be corrected.
Original languageEnglish
Title of host publicationSTeP2000 Millennium of Artificial Intelligence
Subtitle of host publicationAl of Tommorrow
Pages171-178
Number of pages7
Publication statusPublished - 2000
MoE publication typeA4 Article in a conference publication
Event9th Finnish Artificial Intelligence Conference - Espoo, Finland
Duration: 28 Aug 200030 Aug 2000
Conference number: 9

Conference

Conference9th Finnish Artificial Intelligence Conference
CountryFinland
CityEspoo
Period28/08/0030/08/00

Fingerprint

Speech analysis
Acoustics
Hidden Markov models
Speech recognition
Processing

Cite this

Väyrynen, P., Peltola, J., & Seppänen, T. (2000). Enhancing phoneme recogniser performance with a simple rule-based language model. In STeP2000 Millennium of Artificial Intelligence: Al of Tommorrow (pp. 171-178)
Väyrynen, Pertti ; Peltola, Johannes ; Seppänen, Tapio. / Enhancing phoneme recogniser performance with a simple rule-based language model. STeP2000 Millennium of Artificial Intelligence: Al of Tommorrow. 2000. pp. 171-178
@inproceedings{3deec90e27174cc19202f92c243d9c5f,
title = "Enhancing phoneme recogniser performance with a simple rule-based language model",
abstract = "The phoneme classification inaccuracy at the acoustic phonetic level is a major weakness in most speech recognition systems. However, the inaccuracy will violate phonotactic constraints at the acoustic phonetic level. A better performance is expected if a language model is adopted in a recognition system for post-processing phoneme estimates and making corrections with a set of explicit rules of the language used. We developed a simple language model with a set of rules to correct phoneme classification errors made by a Hidden Markov Model based phoneme recognizer. The experimental results indicate that about 20{\%} ofrecognition errors can be corrected.",
author = "Pertti V{\"a}yrynen and Johannes Peltola and Tapio Sepp{\"a}nen",
year = "2000",
language = "English",
isbn = "951-22-5128-0",
pages = "171--178",
booktitle = "STeP2000 Millennium of Artificial Intelligence",

}

Väyrynen, P, Peltola, J & Seppänen, T 2000, Enhancing phoneme recogniser performance with a simple rule-based language model. in STeP2000 Millennium of Artificial Intelligence: Al of Tommorrow. pp. 171-178, 9th Finnish Artificial Intelligence Conference , Espoo, Finland, 28/08/00.

Enhancing phoneme recogniser performance with a simple rule-based language model. / Väyrynen, Pertti; Peltola, Johannes; Seppänen, Tapio.

STeP2000 Millennium of Artificial Intelligence: Al of Tommorrow. 2000. p. 171-178.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Enhancing phoneme recogniser performance with a simple rule-based language model

AU - Väyrynen, Pertti

AU - Peltola, Johannes

AU - Seppänen, Tapio

PY - 2000

Y1 - 2000

N2 - The phoneme classification inaccuracy at the acoustic phonetic level is a major weakness in most speech recognition systems. However, the inaccuracy will violate phonotactic constraints at the acoustic phonetic level. A better performance is expected if a language model is adopted in a recognition system for post-processing phoneme estimates and making corrections with a set of explicit rules of the language used. We developed a simple language model with a set of rules to correct phoneme classification errors made by a Hidden Markov Model based phoneme recognizer. The experimental results indicate that about 20% ofrecognition errors can be corrected.

AB - The phoneme classification inaccuracy at the acoustic phonetic level is a major weakness in most speech recognition systems. However, the inaccuracy will violate phonotactic constraints at the acoustic phonetic level. A better performance is expected if a language model is adopted in a recognition system for post-processing phoneme estimates and making corrections with a set of explicit rules of the language used. We developed a simple language model with a set of rules to correct phoneme classification errors made by a Hidden Markov Model based phoneme recognizer. The experimental results indicate that about 20% ofrecognition errors can be corrected.

M3 - Conference article in proceedings

SN - 951-22-5128-0

SP - 171

EP - 178

BT - STeP2000 Millennium of Artificial Intelligence

ER -

Väyrynen P, Peltola J, Seppänen T. Enhancing phoneme recogniser performance with a simple rule-based language model. In STeP2000 Millennium of Artificial Intelligence: Al of Tommorrow. 2000. p. 171-178