Presentation 2002/1/18
Use of F0 model for the extraction of important sentences in speech summarization
Akira Inoue, Takayoshi Mikami, Yoichi YamashitaTA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) There are possibilities that prosodic information can improve the quality of speech summarization. This paper describes a method of the extraction of important sentences from spoken lectures using F0 parameters as well as linguistic information. The effectiveness of several F0 parameters are investigated for extracting important sentences. We tried some normalized F0 parameters introducing an F0 model that is constructed to predict the value average F0 of the bunsetsu unit in an ordinal utterance. An F0 prarameter is normalized by subtracting a value predicted by the model from a real F0 parameter.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Summarization / F0 model / Speech / Prosodic / Important sentence
Paper #
Date of Issue

Conference Information
Committee SP
Conference Date 2002/1/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Use of F0 model for the extraction of important sentences in speech summarization
Sub Title (in English)
Keyword(1) Summarization
Keyword(2) F0 model
Keyword(3) Speech
Keyword(4) Prosodic
Keyword(5) Important sentence
1st Author's Name Akira Inoue
1st Author's Affiliation Graduate school of Science and Engineering, Ritsumeikan University()
2nd Author's Name Takayoshi Mikami
2nd Author's Affiliation Dep.of Computer Science, Ritsumeikan University
3rd Author's Name Yoichi YamashitaTA
3rd Author's Affiliation Dep.of Computer Science, Ritsumeikan University
Date 2002/1/18
Paper #
Volume (vol) vol.101
Number (no) 604
Page pp.pp.-
#Pages 8
Date of Issue