Presentation 2018-12-11
Speech analysis and synthesis using genetic algorithm and Fujisaki model
Tomio Takara, Ryoichi Eto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a model of infant’s word acquisition by speech mimicking. We use vowel space parameter representing a gesture of articulation. The coarticulation is expressed in Fujisaki model applied to the vowel space parameters. The trial and error in the speech mimicking is modeled in the genetic algorithm. The gesture of articulation is detected as “a command” of Fujisaki model from the ambiguous spectrum. We show the effectiveness of the model by listening tests and detection of the gesture of articulation from the symmetric three vowels and the cut two vowels.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Model of Spoken Word Acquisition / Coarticulation / Fujisaki Model / Genetic Algorithm / Vowel Space Parameter
Paper # SP2018-50
Date of Issue 2018-12-03 (SP)

Conference Information
Committee NLC / IPSJ-NL / SP / IPSJ-SLP
Conference Date 2018/12/10(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Waseda Univ. Nishiwaseda Campus
Topics (in Japanese) (See Japanese page)
Topics (in English) The 5th Natural Language Processing Symposium & The 20th Spoken Language Symposium
Chair Takeshi Sakaki(Hottolink) / / Yoichi Yamashita(Ritsumeikan Univ.)
Vice Chair Mitsuo Yoshida(Toyohashi Univ. of Tech.) / Kazutaka Shimada(Kyushu Inst. of Tech.) / / Akinobu Ri(Nagoya Inst. of Tech.)
Secretary Mitsuo Yoshida(Ryukoku Univ.) / Kazutaka Shimada(NTT) / / Akinobu Ri(Kyoto Univ.) / (Meijo Univ.)
Assistant Takeshi Kobayakawa(NHK) / Hiroki Sakaji(Univ. of Tokyo) / / Tomoki Koriyama(Tokyo Inst. of Tech.) / Satoshi Kobashikawa(NTT)

Paper Information
Registration To Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Natural Language / Technical Committee on Speech / Special Interest Group on Spoken Language Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Speech analysis and synthesis using genetic algorithm and Fujisaki model
Sub Title (in English)
Keyword(1) Model of Spoken Word Acquisition
Keyword(2) Coarticulation
Keyword(3) Fujisaki Model
Keyword(4) Genetic Algorithm
Keyword(5) Vowel Space Parameter
1st Author's Name Tomio Takara
1st Author's Affiliation University of the Ryukyus(Univ. Ryukyus)
2nd Author's Name Ryoichi Eto
2nd Author's Affiliation International Systems(Inter. Sys.)
Date 2018-12-11
Paper # SP2018-50
Volume (vol) vol.118
Number (no) SP-354
Page pp.pp.101-106(SP),
#Pages 6
Date of Issue 2018-12-03 (SP)