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

研究成果: Conference contribution

抄録

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.

本文言語English
ホスト出版物のタイトル6th International Conference on Spoken Language Processing, ICSLP 2000
出版社International Speech Communication Association
ISBN(電子版)7801501144, 9787801501141
出版ステータスPublished - 2000
外部発表はい
イベント6th International Conference on Spoken Language Processing, ICSLP 2000 - Beijing, China
継続期間: 2000 10 162000 10 20

Other

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

ASJC Scopus subject areas

  • 言語学および言語
  • 言語および言語学

フィンガープリント

「Rules, but what for ? - Rule description as efficient and robust abstraction of corpora and optimal fitting to applications-」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル