A hierarchical language model incorporating class-dependent word models for OOV words recognition

Koichi Tanigaki, Hirofumi Yamamoto, Yoshinori Sagisaka

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

17 Citations (Scopus)

Abstract

A new language model is proposed to cope with the demands for recognizing out-of-vocabulary (OOV) words not registered in the lexicon. This language model is a class N-gram incorporating a set of word models that reflect the statistical characteristics of the phonotactics, which depend on the lexical classes. Utilization of class-dependency enhances recognition accuracy and enables identification of the class of OOV words. OOV words can be recognized as transcribed portions having class labels, which provide semantic attributes of OOV words to subsequent language processing. Experimental application of the model to Japanese personal and family names showed that it performs nearly as well as the upper bound of the in-vocabulary recognition.

Original languageEnglish
Title of host publication6th International Conference on Spoken Language Processing, ICSLP 2000
PublisherInternational Speech Communication Association
ISBN (Electronic)7801501144, 9787801501141
Publication statusPublished - 2000
Externally publishedYes
Event6th International Conference on Spoken Language Processing, ICSLP 2000 - Beijing, China
Duration: 2000 Oct 162000 Oct 20

Other

Other6th International Conference on Spoken Language Processing, ICSLP 2000
CountryChina
CityBeijing
Period00/10/1600/10/20

Fingerprint

vocabulary
language
utilization
semantics
Language Model
Word Recognition
Vocabulary

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics

Cite this

Tanigaki, K., Yamamoto, H., & Sagisaka, Y. (2000). A hierarchical language model incorporating class-dependent word models for OOV words recognition. In 6th International Conference on Spoken Language Processing, ICSLP 2000 International Speech Communication Association.

A hierarchical language model incorporating class-dependent word models for OOV words recognition. / Tanigaki, Koichi; Yamamoto, Hirofumi; Sagisaka, Yoshinori.

6th International Conference on Spoken Language Processing, ICSLP 2000. International Speech Communication Association, 2000.

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

Tanigaki, K, Yamamoto, H & Sagisaka, Y 2000, A hierarchical language model incorporating class-dependent word models for OOV words recognition. in 6th International Conference on Spoken Language Processing, ICSLP 2000. International Speech Communication Association, 6th International Conference on Spoken Language Processing, ICSLP 2000, Beijing, China, 00/10/16.
Tanigaki K, Yamamoto H, Sagisaka Y. A hierarchical language model incorporating class-dependent word models for OOV words recognition. In 6th International Conference on Spoken Language Processing, ICSLP 2000. International Speech Communication Association. 2000
Tanigaki, Koichi ; Yamamoto, Hirofumi ; Sagisaka, Yoshinori. / A hierarchical language model incorporating class-dependent word models for OOV words recognition. 6th International Conference on Spoken Language Processing, ICSLP 2000. International Speech Communication Association, 2000.
@inproceedings{32dd2922f5cf44e09145c38bd5666660,
title = "A hierarchical language model incorporating class-dependent word models for OOV words recognition",
abstract = "A new language model is proposed to cope with the demands for recognizing out-of-vocabulary (OOV) words not registered in the lexicon. This language model is a class N-gram incorporating a set of word models that reflect the statistical characteristics of the phonotactics, which depend on the lexical classes. Utilization of class-dependency enhances recognition accuracy and enables identification of the class of OOV words. OOV words can be recognized as transcribed portions having class labels, which provide semantic attributes of OOV words to subsequent language processing. Experimental application of the model to Japanese personal and family names showed that it performs nearly as well as the upper bound of the in-vocabulary recognition.",
author = "Koichi Tanigaki and Hirofumi Yamamoto and Yoshinori Sagisaka",
year = "2000",
language = "English",
booktitle = "6th International Conference on Spoken Language Processing, ICSLP 2000",
publisher = "International Speech Communication Association",

}

TY - GEN

T1 - A hierarchical language model incorporating class-dependent word models for OOV words recognition

AU - Tanigaki, Koichi

AU - Yamamoto, Hirofumi

AU - Sagisaka, Yoshinori

PY - 2000

Y1 - 2000

N2 - A new language model is proposed to cope with the demands for recognizing out-of-vocabulary (OOV) words not registered in the lexicon. This language model is a class N-gram incorporating a set of word models that reflect the statistical characteristics of the phonotactics, which depend on the lexical classes. Utilization of class-dependency enhances recognition accuracy and enables identification of the class of OOV words. OOV words can be recognized as transcribed portions having class labels, which provide semantic attributes of OOV words to subsequent language processing. Experimental application of the model to Japanese personal and family names showed that it performs nearly as well as the upper bound of the in-vocabulary recognition.

AB - A new language model is proposed to cope with the demands for recognizing out-of-vocabulary (OOV) words not registered in the lexicon. This language model is a class N-gram incorporating a set of word models that reflect the statistical characteristics of the phonotactics, which depend on the lexical classes. Utilization of class-dependency enhances recognition accuracy and enables identification of the class of OOV words. OOV words can be recognized as transcribed portions having class labels, which provide semantic attributes of OOV words to subsequent language processing. Experimental application of the model to Japanese personal and family names showed that it performs nearly as well as the upper bound of the in-vocabulary recognition.

UR - http://www.scopus.com/inward/record.url?scp=85009144928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009144928&partnerID=8YFLogxK

M3 - Conference contribution

BT - 6th International Conference on Spoken Language Processing, ICSLP 2000

PB - International Speech Communication Association

ER -