Expanding vocabulary for recognizing user's abbreviations of proper nouns without increasing ASR error rates in spoken dialogue systems

Masaki Katsumaru, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno

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

1 Citation (Scopus)

Abstract

Users often abbreviate long words when using spoken dialogue systems, which results in automatic speech recognition (ASR) errors. We define abbreviated words as sub-words of the original word, and add them into an ASR dictionary. The first problem is that proper nouns cannot be correctly segmented by general morphological analyzers, although long and compounded words need to be segmented in agglutinative languages such as Japanese. The second is that, as vocabulary increases, adding many abbreviated words degrades the ASR accuracy. We develop two methods, (1) to segment words by using conjunction probabilities between characters, and (2) to manipulate occurrence probabilities of generated abbreviated words on the basis of the phonological similarities between abbreviated and original words. By our method, the ASR accuracy is improved by 24.2 points for utterances containing abbreviated words, and degraded by only a 0.1 point for those containing original words.

Original languageEnglish
Title of host publicationProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Pages187-190
Number of pages4
Publication statusPublished - 2008
Externally publishedYes
EventINTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association - Brisbane, QLD, Australia
Duration: 2008 Sep 222008 Sep 26

Other

OtherINTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association
CountryAustralia
CityBrisbane, QLD
Period08/9/2208/9/26

Fingerprint

Vocabulary
Speech recognition
Glossaries
Language

Keywords

  • Abbreviated words
  • Proper nouns
  • Spoken dialogue systems
  • Vocabulary expansion

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Sensory Systems

Cite this

Katsumaru, M., Komatani, K., Ogata, T., & Okuno, H. G. (2008). Expanding vocabulary for recognizing user's abbreviations of proper nouns without increasing ASR error rates in spoken dialogue systems. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp. 187-190)

Expanding vocabulary for recognizing user's abbreviations of proper nouns without increasing ASR error rates in spoken dialogue systems. / Katsumaru, Masaki; Komatani, Kazunori; Ogata, Tetsuya; Okuno, Hiroshi G.

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2008. p. 187-190.

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

Katsumaru, M, Komatani, K, Ogata, T & Okuno, HG 2008, Expanding vocabulary for recognizing user's abbreviations of proper nouns without increasing ASR error rates in spoken dialogue systems. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 187-190, INTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association, Brisbane, QLD, Australia, 08/9/22.
Katsumaru M, Komatani K, Ogata T, Okuno HG. Expanding vocabulary for recognizing user's abbreviations of proper nouns without increasing ASR error rates in spoken dialogue systems. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2008. p. 187-190
Katsumaru, Masaki ; Komatani, Kazunori ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Expanding vocabulary for recognizing user's abbreviations of proper nouns without increasing ASR error rates in spoken dialogue systems. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2008. pp. 187-190
@inproceedings{0c4364c880b94487bec49c21a672166d,
title = "Expanding vocabulary for recognizing user's abbreviations of proper nouns without increasing ASR error rates in spoken dialogue systems",
abstract = "Users often abbreviate long words when using spoken dialogue systems, which results in automatic speech recognition (ASR) errors. We define abbreviated words as sub-words of the original word, and add them into an ASR dictionary. The first problem is that proper nouns cannot be correctly segmented by general morphological analyzers, although long and compounded words need to be segmented in agglutinative languages such as Japanese. The second is that, as vocabulary increases, adding many abbreviated words degrades the ASR accuracy. We develop two methods, (1) to segment words by using conjunction probabilities between characters, and (2) to manipulate occurrence probabilities of generated abbreviated words on the basis of the phonological similarities between abbreviated and original words. By our method, the ASR accuracy is improved by 24.2 points for utterances containing abbreviated words, and degraded by only a 0.1 point for those containing original words.",
keywords = "Abbreviated words, Proper nouns, Spoken dialogue systems, Vocabulary expansion",
author = "Masaki Katsumaru and Kazunori Komatani and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2008",
language = "English",
pages = "187--190",
booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

}

TY - GEN

T1 - Expanding vocabulary for recognizing user's abbreviations of proper nouns without increasing ASR error rates in spoken dialogue systems

AU - Katsumaru, Masaki

AU - Komatani, Kazunori

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2008

Y1 - 2008

N2 - Users often abbreviate long words when using spoken dialogue systems, which results in automatic speech recognition (ASR) errors. We define abbreviated words as sub-words of the original word, and add them into an ASR dictionary. The first problem is that proper nouns cannot be correctly segmented by general morphological analyzers, although long and compounded words need to be segmented in agglutinative languages such as Japanese. The second is that, as vocabulary increases, adding many abbreviated words degrades the ASR accuracy. We develop two methods, (1) to segment words by using conjunction probabilities between characters, and (2) to manipulate occurrence probabilities of generated abbreviated words on the basis of the phonological similarities between abbreviated and original words. By our method, the ASR accuracy is improved by 24.2 points for utterances containing abbreviated words, and degraded by only a 0.1 point for those containing original words.

AB - Users often abbreviate long words when using spoken dialogue systems, which results in automatic speech recognition (ASR) errors. We define abbreviated words as sub-words of the original word, and add them into an ASR dictionary. The first problem is that proper nouns cannot be correctly segmented by general morphological analyzers, although long and compounded words need to be segmented in agglutinative languages such as Japanese. The second is that, as vocabulary increases, adding many abbreviated words degrades the ASR accuracy. We develop two methods, (1) to segment words by using conjunction probabilities between characters, and (2) to manipulate occurrence probabilities of generated abbreviated words on the basis of the phonological similarities between abbreviated and original words. By our method, the ASR accuracy is improved by 24.2 points for utterances containing abbreviated words, and degraded by only a 0.1 point for those containing original words.

KW - Abbreviated words

KW - Proper nouns

KW - Spoken dialogue systems

KW - Vocabulary expansion

UR - http://www.scopus.com/inward/record.url?scp=84867221569&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867221569&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84867221569

SP - 187

EP - 190

BT - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

ER -