Articulation-disordered speech recognition using speaker-adaptive acoustic models and personalized articulation patterns

Chung-Hsien Wu, Hung Yu Su, Han Ping Shen

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

This article presents a novel approach to speaker-adaptive recognition of speech from articulationdisordered speakers without a large amount of adaptation data. An unsupervised, incremental adaptation method is adopted for personalized model adaptation based on the recognized syllables with high recognition confidence from an automatic speech recognition (ASR) system. For articulation pattern discovery, the manually transcribed syllables and the corresponding recognized syllables are associated with each other using articulatory features. The Apriori algorithm is applied to discover the articulation patterns in the corpus, which are then used to construct a personalized pronunciation dictionary to improve the recognition accuracy of the ASR. The experimental results indicate that the proposed adaptation method achieves a syllable error rate reduction of 6.1%, outperforming the conventional adaptation methods that have a syllable error rate reduction of 3.8%. In addition, an average syllable error rate reduction of 5.04% is obtained for the ASR using the expanded pronunciation dictionary.

Original languageEnglish
Article number7
JournalACM Transactions on Asian Language Information Processing
Volume10
Issue number2
DOIs
Publication statusPublished - 2011 Jun

Fingerprint

Speech recognition
Acoustics
Glossaries

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

@article{006f45065d67432283e9059d939d652b,
title = "Articulation-disordered speech recognition using speaker-adaptive acoustic models and personalized articulation patterns",
abstract = "This article presents a novel approach to speaker-adaptive recognition of speech from articulationdisordered speakers without a large amount of adaptation data. An unsupervised, incremental adaptation method is adopted for personalized model adaptation based on the recognized syllables with high recognition confidence from an automatic speech recognition (ASR) system. For articulation pattern discovery, the manually transcribed syllables and the corresponding recognized syllables are associated with each other using articulatory features. The Apriori algorithm is applied to discover the articulation patterns in the corpus, which are then used to construct a personalized pronunciation dictionary to improve the recognition accuracy of the ASR. The experimental results indicate that the proposed adaptation method achieves a syllable error rate reduction of 6.1{\%}, outperforming the conventional adaptation methods that have a syllable error rate reduction of 3.8{\%}. In addition, an average syllable error rate reduction of 5.04{\%} is obtained for the ASR using the expanded pronunciation dictionary.",
author = "Chung-Hsien Wu and Su, {Hung Yu} and Shen, {Han Ping}",
year = "2011",
month = "6",
doi = "10.1145/1967293.1967294",
language = "English",
volume = "10",
journal = "ACM Transactions on Asian Language Information Processing",
issn = "1530-0226",
publisher = "Association for Computing Machinery (ACM)",
number = "2",

}

TY - JOUR

T1 - Articulation-disordered speech recognition using speaker-adaptive acoustic models and personalized articulation patterns

AU - Wu, Chung-Hsien

AU - Su, Hung Yu

AU - Shen, Han Ping

PY - 2011/6

Y1 - 2011/6

N2 - This article presents a novel approach to speaker-adaptive recognition of speech from articulationdisordered speakers without a large amount of adaptation data. An unsupervised, incremental adaptation method is adopted for personalized model adaptation based on the recognized syllables with high recognition confidence from an automatic speech recognition (ASR) system. For articulation pattern discovery, the manually transcribed syllables and the corresponding recognized syllables are associated with each other using articulatory features. The Apriori algorithm is applied to discover the articulation patterns in the corpus, which are then used to construct a personalized pronunciation dictionary to improve the recognition accuracy of the ASR. The experimental results indicate that the proposed adaptation method achieves a syllable error rate reduction of 6.1%, outperforming the conventional adaptation methods that have a syllable error rate reduction of 3.8%. In addition, an average syllable error rate reduction of 5.04% is obtained for the ASR using the expanded pronunciation dictionary.

AB - This article presents a novel approach to speaker-adaptive recognition of speech from articulationdisordered speakers without a large amount of adaptation data. An unsupervised, incremental adaptation method is adopted for personalized model adaptation based on the recognized syllables with high recognition confidence from an automatic speech recognition (ASR) system. For articulation pattern discovery, the manually transcribed syllables and the corresponding recognized syllables are associated with each other using articulatory features. The Apriori algorithm is applied to discover the articulation patterns in the corpus, which are then used to construct a personalized pronunciation dictionary to improve the recognition accuracy of the ASR. The experimental results indicate that the proposed adaptation method achieves a syllable error rate reduction of 6.1%, outperforming the conventional adaptation methods that have a syllable error rate reduction of 3.8%. In addition, an average syllable error rate reduction of 5.04% is obtained for the ASR using the expanded pronunciation dictionary.

UR - http://www.scopus.com/inward/record.url?scp=79960828495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960828495&partnerID=8YFLogxK

U2 - 10.1145/1967293.1967294

DO - 10.1145/1967293.1967294

M3 - Article

VL - 10

JO - ACM Transactions on Asian Language Information Processing

JF - ACM Transactions on Asian Language Information Processing

SN - 1530-0226

IS - 2

M1 - 7

ER -