News

https://www.nime.org/proc/nime2023_94/index.html Atsuya Kobayashi, Ryo Nishikado, and Nao Tokui. 2023. Improvise+=Chain: Listening to the Ensemble Improvisation of an Autoregressive Generative Model. Proceedings of the International Conference on New Interfaces for Musical Expression. Abstract: This paper describes Improvise+=Chain, an audio-visual installation artwork of autonomous musical performance using artificial intelligence technology. The work is designed to provide the audience…

合ベルヌーイ分布を用いた音楽生成モデルの提案を行う. ガウス分布を用いて画像を生成するDiffusion Modelは, シンボリックなデータであるMIDIを直接生成することが難しい. そこで音符のオンオフをベルヌーイ分布を用いて表現することでシンボリックデータへの適用行った. 本稿では, その生成結果と評価について報告する. Nobusue RyukuTokui Nao Paper submission destination：Information Processing Society of Japan

Kai Obara Ryo Hasegawa Ryo Nishikado Dai Takanashi Nao Tokui In this research, we use a loop sound source extraction algorithm to create a loop sound source with 8 beats of periodicity for a song requested by an audience (such as an online live audience) through a music streaming service.We used a sound source separation…

Tokui, N. (2020) ‘Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin’, Available at: http://arxiv.org/abs/2004.01525. There has been significant progress in the music generation technique utilizing deep learning. However, it is still hard for musicians and artists to use these techniques in their daily music-making practice. This paper proposes…

Proceedings of the International Conference on New Interfaces for Musical Expression.