Title:
INFORMATION PROCESSING METHOD, INFORMATION PROCESSING DEVICE, AND INFORMATION PROCESSING PROGRAM
Document Type and Number:
WIPO Patent Application WO/2021/225008
Kind Code:
A1
Abstract:
This information processing method generates, using a plurality of features that are not in a connected relationship and a trained model, new data obtained from a plurality of changed features, and the trained model outputs the plurality of changed features in response to the input of the plurality of features.
Inventors:
AKAMA TAKETO (JP)
Application Number:
PCT/JP2020/031356
Publication Date:
November 11, 2021
Filing Date:
August 19, 2020
Export Citation:
Assignee:
SONY GROUP CORP (JP)
International Classes:
G06N20/00
Domestic Patent References:
| WO2020080268A1 | 2020-04-23 |
Foreign References:
| JP2002032077A | 2002-01-31 |
Other References:
SASAKI, MANA : "A study of melody editing method by automatic interpolation of melody", IPSJ SIG TECHNICAL REPORT, SPOKEN LANGUAGE INFORMATION PROCESSING (SLP), vol. 2018-SLP-122, no. 24, 16 June 2018 (2018-06-16), pages 1 - 4, XP009540784
GINO BRUNNER; ANDRES KONRAD; YUYI WANG; ROGER WATTENHOFER: "MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 20 September 2018 (2018-09-20), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081193478
JUNYAN, J. ET AL., STYLISTIC MELODY GENERATION WITH CONDITIONAL VARIATIONAL AUTO-ENCODER [ ONLINE, 2019, XP055873182, Retrieved from the Internet [retrieved on 20201112]
ROBERTS ADAM, AL.: "MusicVAE: Creating a palette for musical scores with machine learning.", MAGENTA, GOOGLE AI, 15 March 2018 (2018-03-15), XP055817753, Retrieved from the Internet [retrieved on 20210624]
ANONYMOUS: "Style transfer for creative art ", WOLFRAM LANGUAGE, pages 1 - 3, XP055971193, Retrieved from the Internet [retrieved on 20221014]
ANONYMOUS: "Converting videos into styles of van Gogh, etc. in real time; technology under development by Google", GIGAZINE, pages 1 - 10, XP055971194, Retrieved from the Internet [retrieved on 20221014]
SUGIYAMA, SUSUMU ET AL.: "Building a talker vector space with variational autoencoder and its parallel data-free talker transformation", IPSJ TECHNICAL REPORT MUSIC INFORMATION SCIENCE (MUS), vol. 2018-MUS-119, no. 28, 16 June 2018 (2018-06-16), pages 1 - 6, XP009540785
GINO BRUNNER; ANDRES KONRAD; YUYI WANG; ROGER WATTENHOFER: "MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 20 September 2018 (2018-09-20), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081193478
JUNYAN, J. ET AL., STYLISTIC MELODY GENERATION WITH CONDITIONAL VARIATIONAL AUTO-ENCODER [ ONLINE, 2019, XP055873182, Retrieved from the Internet
ROBERTS ADAM, AL.: "MusicVAE: Creating a palette for musical scores with machine learning.", MAGENTA, GOOGLE AI, 15 March 2018 (2018-03-15), XP055817753, Retrieved from the Internet
ANONYMOUS: "Style transfer for creative art ", WOLFRAM LANGUAGE, pages 1 - 3, XP055971193, Retrieved from the Internet
ANONYMOUS: "Converting videos into styles of van Gogh, etc. in real time; technology under development by Google", GIGAZINE, pages 1 - 10, XP055971194, Retrieved from the Internet
SUGIYAMA, SUSUMU ET AL.: "Building a talker vector space with variational autoencoder and its parallel data-free talker transformation", IPSJ TECHNICAL REPORT MUSIC INFORMATION SCIENCE (MUS), vol. 2018-MUS-119, no. 28, 16 June 2018 (2018-06-16), pages 1 - 6, XP009540785
Attorney, Agent or Firm:
SAKAI INTERNATIONAL PATENT OFFICE (JP)
Download PDF: