Presentation 2024-03-11
A Method of Timbre Synthesis Reflecting Impression Using Conditional-VAE
Miyu Yoshikawa, Susumu Kuroyanagi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is difficult to systematically explain the relationship between tones and the impressions people have of them. In this paper, we have used a conditional variational autoencoder (CVAE)to generate tones based on the impressions that humans evoke.We aim to expand the variation of tones represented, and the model was extended based on the idea that temporal changes in waveform amplitude are important for the recall of impressions. Therefore, we separated the model into a waveform formed by the overtone composition ratio and envelope information, which is the temporal variation of the amplitude, and each was learned by the CVAE. The effectiveness of the proposed method is demonstrated through listening experiments with subjects.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Timbre synthesis / Conditional variational autoencoder / Impression
Paper # NC2023-49
Date of Issue 2024-03-04 (NC)

Conference Information
Committee NC / MBE
Conference Date 2024/3/11(2days)
Place (in Japanese) (See Japanese page)
Place (in English) The Univ. of Tokyo
Topics (in Japanese) (See Japanese page)
Topics (in English) Brain architecture, General
Chair Hirokazu Tanaka(Tokyo City Univ.) / Hisashi Yoshida(Kinki Univ.)
Vice Chair Jun Izawa(Univ. of Tsukub) / Akinori Ueno(Tokyo Denki Univ.)
Secretary Jun Izawa(NTT) / Akinori Ueno(NAIST)
Assistant Yoshimasa Tawatsuji(Waseda Univ.) / Takato Horii(Osaka Univ.) / Akihiko Tsukahara(Tokyo Denki Univ.) / Miki Kaneko(Osaka Univ.)

Paper Information
Registration To Technical Committee on Neurocomputing / Technical Committee on ME and Bio Cybernetics
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Method of Timbre Synthesis Reflecting Impression Using Conditional-VAE
Sub Title (in English) Applying the Temporal Information
Keyword(1) Timbre synthesis
Keyword(2) Conditional variational autoencoder
Keyword(3) Impression
1st Author's Name Miyu Yoshikawa
1st Author's Affiliation Nagoya Institute of Technology(NIT)
2nd Author's Name Susumu Kuroyanagi
2nd Author's Affiliation Nagoya Institute of Technology(NIT)
Date 2024-03-11
Paper # NC2023-49
Volume (vol) vol.123
Number (no) NC-418
Page pp.pp.37-42(NC),
#Pages 6
Date of Issue 2024-03-04 (NC)