Title:
MUSICAL COMPOSITION GENERATION DEVICE, MUSICAL COMPOSITION SIMILARITY DETERMINATION DEVICE, MUSICAL COMPOSITION GENERATION METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2024/079865
Kind Code:
A1
Abstract:
Provided is a musical composition generation device that comprises an encoder that converts audio data for first and second musical compositions to first and second feature vectors within a first feature space and a decoder that generates audio data on the basis of a third feature vector obtained by synthesizing the first and second feature vectors.
Inventors:
WU YIMING (JP)
Application Number:
PCT/JP2022/038294
Publication Date:
April 18, 2024
Filing Date:
October 14, 2022
Export Citation:
Assignee:
ALPHATHETA CORP (JP)
International Classes:
G10H1/00
Domestic Patent References:
| WO2020080239A1 | 2020-04-23 |
Foreign References:
| JP2022022294A | 2022-02-03 | |||
| JP2022065554A | 2022-04-27 |
Other References:
ADAM ROBERTS: "A hierarchical latent vector model for learning long-term structure in music", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, ARXIV.ORG, ITHACA, 11 November 2019 (2019-11-11), Ithaca, pages 1 - 16, XP093157559, Retrieved from the Internet DOI: 10.48550/arXiv.1803.05428
TATSUNORI HIRAI: "Comparison of generative deep learning models targeting melodies", IPSJ SIG TECHNICAL REPORT, INFORMATION PROCESSING SOCIETY OF JAPAN, vol. .2021-MUS-130, no. 15, 1 January 2021 (2021-01-01), pages 1 - 12, XP093157561
HIRONORI YAMAMOTO: "Music Composition based on the Genetic Programming with segmented VRAE * 1", THE 33RD ANNUAL CONFERENCE OF THE JAPANESE SOCIETY FOR ARTIFICIAL INTELLIGENCE, 2019, 1 June 2019 (2019-06-01) - 7 June 2019 (2019-06-07), pages 1 - 4, XP093157564
TATSUNORI HIRAI: "Comparison of generative deep learning models targeting melodies", IPSJ SIG TECHNICAL REPORT, INFORMATION PROCESSING SOCIETY OF JAPAN, vol. .2021-MUS-130, no. 15, 1 January 2021 (2021-01-01), pages 1 - 12, XP093157561
HIRONORI YAMAMOTO: "Music Composition based on the Genetic Programming with segmented VRAE * 1", THE 33RD ANNUAL CONFERENCE OF THE JAPANESE SOCIETY FOR ARTIFICIAL INTELLIGENCE, 2019, 1 June 2019 (2019-06-01) - 7 June 2019 (2019-06-07), pages 1 - 4, XP093157564
Attorney, Agent or Firm:
KINOSHITA & ASSOCIATES (JP)
Download PDF: