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

Koichi Tanigaki; Hirofumi Yamamoto; Yoshinori Sagisaka

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 proceeding › Conference contribution

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 language	English
Title of host publication	6th International Conference on Spoken Language Processing, ICSLP 2000
Publisher	International Speech Communication Association
ISBN (Electronic)	7801501144, 9787801501141
Publication status	Published - 2000
Externally published	Yes
Event	6th International Conference on Spoken Language Processing, ICSLP 2000 - Beijing, China Duration: 2000 Oct 16 → 2000 Oct 20

Other

Other	6th International Conference on Spoken Language Processing, ICSLP 2000
Country/Territory	China
City	Beijing
Period	00/10/16 → 00/10/20

ASJC Scopus subject areas

Linguistics and Language
Language and Linguistics

Cite this

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 proceeding › Conference contribution

@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",

note = "6th International Conference on Spoken Language Processing, ICSLP 2000 ; Conference date: 16-10-2000 Through 20-10-2000",

}

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

AN - SCOPUS:85009144928

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

PB - International Speech Communication Association

T2 - 6th International Conference on Spoken Language Processing, ICSLP 2000

Y2 - 16 October 2000 through 20 October 2000

ER -

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

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this