New language models using phrase structures extracted from parse trees

Takatoshi Jitsuhiro, Hirofumi Yamamoto, Setsuo Yamada, Yoshinori Sagisaka

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

Abstract

This paper proposes a new speech recognition scheme using three linguistic constraints. Multi-class composite bigram models [1] are used in the first and second passes to reflect word-neighboring characteristics as an extension of conventional word n-gram models. Trigram models with constituent boundary markers and word pattern models are both used in the third pass to utilize phrasal constraints and headword co-occurrences, respectively. These two models are made using a training text corpus with phrase structures given by an example based Transfer-Driven Machine Translation (TDMT) parser [2]. Speech recognition experiments show that the new recognition scheme reduces word errors 9.50% from the conventional scheme by using word-neighboring characteristics, that is only the multi-class composite bigram models.

Original languageEnglish
Title of host publicationEUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology
PublisherInternational Speech Communication Association
Pages697-700
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

language
Speech recognition
Composite materials
Linguistics
linguistics
experiment
Experiments

ASJC Scopus subject areas

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

Cite this

Jitsuhiro, T., Yamamoto, H., Yamada, S., & Sagisaka, Y. (2001). New language models using phrase structures extracted from parse trees. In EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology (pp. 697-700). International Speech Communication Association.

New language models using phrase structures extracted from parse trees. / Jitsuhiro, Takatoshi; Yamamoto, Hirofumi; Yamada, Setsuo; Sagisaka, Yoshinori.

EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, 2001. p. 697-700.

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

Jitsuhiro, T, Yamamoto, H, Yamada, S & Sagisaka, Y 2001, New language models using phrase structures extracted from parse trees. in EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, pp. 697-700, 7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001, Aalborg, Denmark, 01/9/3.
Jitsuhiro T, Yamamoto H, Yamada S, Sagisaka Y. New language models using phrase structures extracted from parse trees. In EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association. 2001. p. 697-700
Jitsuhiro, Takatoshi ; Yamamoto, Hirofumi ; Yamada, Setsuo ; Sagisaka, Yoshinori. / New language models using phrase structures extracted from parse trees. EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, 2001. pp. 697-700
@inproceedings{8e411170a10b48988e6a562ea78f6863,
title = "New language models using phrase structures extracted from parse trees",
abstract = "This paper proposes a new speech recognition scheme using three linguistic constraints. Multi-class composite bigram models [1] are used in the first and second passes to reflect word-neighboring characteristics as an extension of conventional word n-gram models. Trigram models with constituent boundary markers and word pattern models are both used in the third pass to utilize phrasal constraints and headword co-occurrences, respectively. These two models are made using a training text corpus with phrase structures given by an example based Transfer-Driven Machine Translation (TDMT) parser [2]. Speech recognition experiments show that the new recognition scheme reduces word errors 9.50{\%} from the conventional scheme by using word-neighboring characteristics, that is only the multi-class composite bigram models.",
author = "Takatoshi Jitsuhiro and Hirofumi Yamamoto and Setsuo Yamada and Yoshinori Sagisaka",
year = "2001",
language = "English",
pages = "697--700",
booktitle = "EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology",
publisher = "International Speech Communication Association",

}

TY - GEN

T1 - New language models using phrase structures extracted from parse trees

AU - Jitsuhiro, Takatoshi

AU - Yamamoto, Hirofumi

AU - Yamada, Setsuo

AU - Sagisaka, Yoshinori

PY - 2001

Y1 - 2001

N2 - This paper proposes a new speech recognition scheme using three linguistic constraints. Multi-class composite bigram models [1] are used in the first and second passes to reflect word-neighboring characteristics as an extension of conventional word n-gram models. Trigram models with constituent boundary markers and word pattern models are both used in the third pass to utilize phrasal constraints and headword co-occurrences, respectively. These two models are made using a training text corpus with phrase structures given by an example based Transfer-Driven Machine Translation (TDMT) parser [2]. Speech recognition experiments show that the new recognition scheme reduces word errors 9.50% from the conventional scheme by using word-neighboring characteristics, that is only the multi-class composite bigram models.

AB - This paper proposes a new speech recognition scheme using three linguistic constraints. Multi-class composite bigram models [1] are used in the first and second passes to reflect word-neighboring characteristics as an extension of conventional word n-gram models. Trigram models with constituent boundary markers and word pattern models are both used in the third pass to utilize phrasal constraints and headword co-occurrences, respectively. These two models are made using a training text corpus with phrase structures given by an example based Transfer-Driven Machine Translation (TDMT) parser [2]. Speech recognition experiments show that the new recognition scheme reduces word errors 9.50% from the conventional scheme by using word-neighboring characteristics, that is only the multi-class composite bigram models.

UR - http://www.scopus.com/inward/record.url?scp=85009072522&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009072522&partnerID=8YFLogxK

M3 - Conference contribution

SP - 697

EP - 700

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

PB - International Speech Communication Association

ER -