Presentation 2023-09-22
A Method of Generating Images to Represent Impressions of a Piece of Music Using the Text2Image Model
Shoichi Sasaki, Taketoshi Ushiama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we propose a method for automatically generating images that represent impressions of songs using information on song lyrics and the Text2Image model. Specifically, we analyze the meaning of the lyrics to create a prompt suitable for image generation, and then input the prompt to the Text2Image model to obtain an image. We then conduct subject experiments to verify the validity of the generated images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Music analysis / Image generation / Text2Image / Text impression analysis / Information extraction
Paper # DE2023-26
Date of Issue 2023-09-14 (DE)

Conference Information
Committee DE / IPSJ-DBS / IPSJ-IFAT
Conference Date 2023/9/21(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kitakyushu International Conference Center
Topics (in Japanese) (See Japanese page)
Topics (in English) Bigdata management, information retrieval, knowledge discovery, etc.
Chair Masashi Toyoda(Univ. of Tokyo)
Vice Chair Kosuke Takano(Kanagawa Inst. of Tech.) / Chiemi Watanabe(Tsukuba Univ. of Technology)
Secretary Kosuke Takano(Univ. of Tsukuba) / Chiemi Watanabe(Komazawa Univ.)
Assistant Takahiro Komamizu(Nagoya Univ.)

Paper Information
Registration To Technical Committee on Data Engineering / Special Interest Group on Database System / Special Interest Group on Information Fundamentals and Access Technologies
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Method of Generating Images to Represent Impressions of a Piece of Music Using the Text2Image Model
Sub Title (in English)
Keyword(1) Music analysis
Keyword(2) Image generation
Keyword(3) Text2Image
Keyword(4) Text impression analysis
Keyword(5) Information extraction
1st Author's Name Shoichi Sasaki
1st Author's Affiliation Kyushu University(Kyushu Univ.)
2nd Author's Name Taketoshi Ushiama
2nd Author's Affiliation Kyushu University(Kyushu Univ.)
Date 2023-09-22
Paper # DE2023-26
Volume (vol) vol.123
Number (no) DE-192
Page pp.pp.89-94(DE),
#Pages 6
Date of Issue 2023-09-14 (DE)