Art

J-GLOBAL ID：201602270820637928   Reference number：16A1012565

Whisper to normal speech conversion using pitch estimated from spectrum

スペクトルからの推定音高を用いた囁きの正常音声への変換

Author (4)： Konno Hideaki (Hakodate Campus, Hokkaido University of Education, 1-2 Hachiman-cho, Hakodate, Hokkaido 040-8567, Japan) ,  Kudo Mineichi (Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Hokkaido 060-0814, Japan) ,  Imai Hideyuki (Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Hokkaido 060-0814, Japan) ,  Sugimoto Masanori (Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Hokkaido 060-0814, Japan)
Material： Speech Communication  (Speech Commun)
Volume： 83  Page： 10-20  Publication year： Oct. 2016 
JST Material Number： W1590A  ISSN： 0167-6393  Document type： Article
Article type： 原著論文  Country of issue： Netherlands (NLD)  Language： ENGLISH (EN)

Thesaurus term： *speech processing ,  *signal conversion ,  spectrum ,  speech signal ,  speech recognition ,  sound pitch ,  signal estimation ,  Voice ,  Vocal Cords ,  fundamental frequency ,  Japanese ,  Regression Analysis ,  *voice conversion ,  speech spectrum ,  pitch estimation ,  vocal cord vibration ,  phonic organ
Semi thesaurus term： pitch ,  fundamental frequency ,  regression analysis

Author keywords (5)： Whispered speech ,  Pitch ,  Mel-scaled filter bank ,  Principal component analysis ,  Multiple regression analysis

JST classification (2)： Speach processing  (JE05000E) ,  Acoustic signal processing  (BB03050C)

Terms in the title (4)： スペクトル ,  推定 ,  音高 ,  音声