Structured language model for class identification of out-of-vocabulary words arising from multiple word-classes

Shigehiko Onishi, Hirofumi Yamamoto, Yoshinori Sagisaka

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

8 Citations (Scopus)

Abstract

A structured language model (STLM) is proposed to cope with out-of-vocabulary (OOV) words coming from multiple wond-classes. tie STLM aims at independently modeling the classes without interference and identifying the class of words arising from multiple word-classes. The STLM consists of the conventional word-class N-gram and the sets of the independent-Trained class-specific sub-wond N-grams. We made an experimental language model by using STLM for the two similar proper-noun classes and performed the speech recognition experiments. The results show that any OOV word of the one class is never misrecognized as that of the other class. The results show that the STLM could integrate the multiple different statistical language models with no interference.

Original languageEnglish
Title of host publicationEUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology
PublisherInternational Speech Communication Association
Pages693-696
Number of pages4
ISBN (Electronic)8790834100, 9788790834104
Publication statusPublished - 2001
Externally publishedYes
Event7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001 - Aalborg, Denmark
Duration: 2001 Sep 32001 Sep 7

Other

Other7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001
CountryDenmark
CityAalborg
Period01/9/301/9/7

Fingerprint

class identification
vocabulary
Identification (control systems)
language
interference
Speech recognition
experiment

ASJC Scopus subject areas

  • Communication
  • Linguistics and Language
  • Computer Science Applications
  • Software

Cite this

Onishi, S., Yamamoto, H., & Sagisaka, Y. (2001). Structured language model for class identification of out-of-vocabulary words arising from multiple word-classes. In EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology (pp. 693-696). International Speech Communication Association.

Structured language model for class identification of out-of-vocabulary words arising from multiple word-classes. / Onishi, Shigehiko; Yamamoto, Hirofumi; Sagisaka, Yoshinori.

EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, 2001. p. 693-696.

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

Onishi, S, Yamamoto, H & Sagisaka, Y 2001, Structured language model for class identification of out-of-vocabulary words arising from multiple word-classes. in EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, pp. 693-696, 7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001, Aalborg, Denmark, 01/9/3.
Onishi S, Yamamoto H, Sagisaka Y. Structured language model for class identification of out-of-vocabulary words arising from multiple word-classes. In EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association. 2001. p. 693-696
Onishi, Shigehiko ; Yamamoto, Hirofumi ; Sagisaka, Yoshinori. / Structured language model for class identification of out-of-vocabulary words arising from multiple word-classes. EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, 2001. pp. 693-696
@inproceedings{6ff6baeed6ad4f9c8c2dab84e0bf761d,
title = "Structured language model for class identification of out-of-vocabulary words arising from multiple word-classes",
abstract = "A structured language model (STLM) is proposed to cope with out-of-vocabulary (OOV) words coming from multiple wond-classes. tie STLM aims at independently modeling the classes without interference and identifying the class of words arising from multiple word-classes. The STLM consists of the conventional word-class N-gram and the sets of the independent-Trained class-specific sub-wond N-grams. We made an experimental language model by using STLM for the two similar proper-noun classes and performed the speech recognition experiments. The results show that any OOV word of the one class is never misrecognized as that of the other class. The results show that the STLM could integrate the multiple different statistical language models with no interference.",
author = "Shigehiko Onishi and Hirofumi Yamamoto and Yoshinori Sagisaka",
year = "2001",
language = "English",
pages = "693--696",
booktitle = "EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology",
publisher = "International Speech Communication Association",

}

TY - GEN

T1 - Structured language model for class identification of out-of-vocabulary words arising from multiple word-classes

AU - Onishi, Shigehiko

AU - Yamamoto, Hirofumi

AU - Sagisaka, Yoshinori

PY - 2001

Y1 - 2001

N2 - A structured language model (STLM) is proposed to cope with out-of-vocabulary (OOV) words coming from multiple wond-classes. tie STLM aims at independently modeling the classes without interference and identifying the class of words arising from multiple word-classes. The STLM consists of the conventional word-class N-gram and the sets of the independent-Trained class-specific sub-wond N-grams. We made an experimental language model by using STLM for the two similar proper-noun classes and performed the speech recognition experiments. The results show that any OOV word of the one class is never misrecognized as that of the other class. The results show that the STLM could integrate the multiple different statistical language models with no interference.

AB - A structured language model (STLM) is proposed to cope with out-of-vocabulary (OOV) words coming from multiple wond-classes. tie STLM aims at independently modeling the classes without interference and identifying the class of words arising from multiple word-classes. The STLM consists of the conventional word-class N-gram and the sets of the independent-Trained class-specific sub-wond N-grams. We made an experimental language model by using STLM for the two similar proper-noun classes and performed the speech recognition experiments. The results show that any OOV word of the one class is never misrecognized as that of the other class. The results show that the STLM could integrate the multiple different statistical language models with no interference.

UR - http://www.scopus.com/inward/record.url?scp=29744466388&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=29744466388&partnerID=8YFLogxK

M3 - Conference contribution

SP - 693

EP - 696

BT - EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

PB - International Speech Communication Association

ER -