Rules, but what for ? - Rule description as efficient and robust abstraction of corpora and optimal fitting to applications-

Yoshinori Sagisaka, Hirofumi Yamamoto, Minoru Tsuzaki, Hiroaki Kato

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

Abstract

Two recent studies are introduced in speech recognition and speech synthesis to reconsider what rules should be looked for spoken language science and technology. To abstract the neighboring characteristics expressed by N-grams, multi-class composite N-grams have been proposed to model POS characteristics and inflectional forms separately. It is shown that statistical clustering can provide more compact and robust description of word neighboring characteristics than conventional N-grams. For speech synthesis, segmental duration modeling has been examined from the viewpoint of perceptual characteristics of duration changes. A series of perceptual experiments have shown the context dependency of sensitivity to duration change. These two examples respectively illustrate how current rules are interpreted to build scientifically acceptable engineering models and remind us of the deeper scientific meaning and limitation of generalization as a rule.

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

abstraction
spoken language
engineering
experiment
science
N-gram
Speech Synthesis

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics

Cite this

Sagisaka, Y., Yamamoto, H., Tsuzaki, M., & Kato, H. (2000). Rules, but what for ? - Rule description as efficient and robust abstraction of corpora and optimal fitting to applications-. In 6th International Conference on Spoken Language Processing, ICSLP 2000 International Speech Communication Association.

Rules, but what for ? - Rule description as efficient and robust abstraction of corpora and optimal fitting to applications-. / Sagisaka, Yoshinori; Yamamoto, Hirofumi; Tsuzaki, Minoru; Kato, Hiroaki.

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

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

Sagisaka, Y, Yamamoto, H, Tsuzaki, M & Kato, H 2000, Rules, but what for ? - Rule description as efficient and robust abstraction of corpora and optimal fitting to applications-. 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.
Sagisaka Y, Yamamoto H, Tsuzaki M, Kato H. Rules, but what for ? - Rule description as efficient and robust abstraction of corpora and optimal fitting to applications-. In 6th International Conference on Spoken Language Processing, ICSLP 2000. International Speech Communication Association. 2000
Sagisaka, Yoshinori ; Yamamoto, Hirofumi ; Tsuzaki, Minoru ; Kato, Hiroaki. / Rules, but what for ? - Rule description as efficient and robust abstraction of corpora and optimal fitting to applications-. 6th International Conference on Spoken Language Processing, ICSLP 2000. International Speech Communication Association, 2000.
@inproceedings{20086640b2c041588792ab8107755241,
title = "Rules, but what for ? - Rule description as efficient and robust abstraction of corpora and optimal fitting to applications-",
abstract = "Two recent studies are introduced in speech recognition and speech synthesis to reconsider what rules should be looked for spoken language science and technology. To abstract the neighboring characteristics expressed by N-grams, multi-class composite N-grams have been proposed to model POS characteristics and inflectional forms separately. It is shown that statistical clustering can provide more compact and robust description of word neighboring characteristics than conventional N-grams. For speech synthesis, segmental duration modeling has been examined from the viewpoint of perceptual characteristics of duration changes. A series of perceptual experiments have shown the context dependency of sensitivity to duration change. These two examples respectively illustrate how current rules are interpreted to build scientifically acceptable engineering models and remind us of the deeper scientific meaning and limitation of generalization as a rule.",
author = "Yoshinori Sagisaka and Hirofumi Yamamoto and Minoru Tsuzaki and Hiroaki Kato",
year = "2000",
language = "English",
booktitle = "6th International Conference on Spoken Language Processing, ICSLP 2000",
publisher = "International Speech Communication Association",

}

TY - GEN

T1 - Rules, but what for ? - Rule description as efficient and robust abstraction of corpora and optimal fitting to applications-

AU - Sagisaka, Yoshinori

AU - Yamamoto, Hirofumi

AU - Tsuzaki, Minoru

AU - Kato, Hiroaki

PY - 2000

Y1 - 2000

N2 - Two recent studies are introduced in speech recognition and speech synthesis to reconsider what rules should be looked for spoken language science and technology. To abstract the neighboring characteristics expressed by N-grams, multi-class composite N-grams have been proposed to model POS characteristics and inflectional forms separately. It is shown that statistical clustering can provide more compact and robust description of word neighboring characteristics than conventional N-grams. For speech synthesis, segmental duration modeling has been examined from the viewpoint of perceptual characteristics of duration changes. A series of perceptual experiments have shown the context dependency of sensitivity to duration change. These two examples respectively illustrate how current rules are interpreted to build scientifically acceptable engineering models and remind us of the deeper scientific meaning and limitation of generalization as a rule.

AB - Two recent studies are introduced in speech recognition and speech synthesis to reconsider what rules should be looked for spoken language science and technology. To abstract the neighboring characteristics expressed by N-grams, multi-class composite N-grams have been proposed to model POS characteristics and inflectional forms separately. It is shown that statistical clustering can provide more compact and robust description of word neighboring characteristics than conventional N-grams. For speech synthesis, segmental duration modeling has been examined from the viewpoint of perceptual characteristics of duration changes. A series of perceptual experiments have shown the context dependency of sensitivity to duration change. These two examples respectively illustrate how current rules are interpreted to build scientifically acceptable engineering models and remind us of the deeper scientific meaning and limitation of generalization as a rule.

UR - http://www.scopus.com/inward/record.url?scp=85009115314&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009115314&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85009115314

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

PB - International Speech Communication Association

ER -