By Weihan Xu, Julian McAuley, Taylor Berg-Kirkpatrick, Shlomo Dubnov,Hao-Wen Dong ISMIR Late-Breaking Demos, Nov 2024, San Francisco, United States Read full publication. Abstract: Recent years have seen many audio-domain text-to-music generation models that rely on large amounts of text-audio pairs for training. However, similar attempts for symbolic-domain controllable music generation has been hindered due to […]
Ke Chen, Xingjian Du, Bilei Zhu, Zejun Ma, Taylor Berg-Kirkpatrick, Shlomo Dubnov ICASSP 2022 – 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022, Singapore, France. pp.646-650 Read full publication. Abstract: Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention […]
Ke Chen, Hao-Wen Dong, Yi Luo, Julian Mcauley, Taylor Berg-Kirkpatrick, Miller Puckette, Shlomo Dubnov Proceedings of the 23rd International Society for Music Information Retrieval Conference, Dec 2022, Bengaluru, India. Read full publication. Abstract: Choral music separation refers to the task of extracting tracks of voice parts (e.g., soprano, alto, tenor, and bass) from mixed audio. […]
Shlomo Dubnov, Ke Chen, Kevin Huang Journal of Creative Music Systems, 2022, 1 Read full publication. Abstract: Generative musical models often comprise of multiple levels of structure, presuming that the process of composition moves between background to foreground, or between generating musical surface and some deeper and reduced representation that governs hidden or latent dimensions […]
Nikita Srivatsan, Ke Chen, Shlomo Dubnov, Taylor Berg-Kirkpatrick Thirty-Third International Joint Conference on Artificial Intelligence {IJCAI-24}, Aug 2023, Jeju, South Korea. pp.7762-7770. Read full publication. Abstract: In this paper we put forward a new approach to music captioning, the task of automatically generating natural language descriptions for songs. These descriptions are useful both for categorization […]
Marco Fiorini has been invited to lead a workshop at Università di Pisa on 4 November 2024, showcasing REACH advancements in Music Improvisation with Co-Creative Agents. The workshop focused on Somax2, REACH co-creative environment for music improvisation, and saw a wide number of students from Università di Pisa interacting for the first time with it.A […]
Marc ChemillierFranck Jedrzejewski; Carlos Lobo; Antonia Soulez. Écrire comme composer. Le rôle des diagrammes, Éditions Delatour, pp.77-90, 2021, Musique/Philosophie, 9782752104267 Read full publication. Abstract: Les interfaces visuelles des logiciels musicaux sont des diagrammes dans un sens graphique, mais ce sont aussi des diagrammes dans un sens plus conceptuel car ils déterminent une certaine manière de […]
By Marc Chemillier, Jean-Pierre Cholleton. Read full publication. Abstract: Le langage harmonique d’Hermeto Pascoal et son apprentissage par une intelligenceartificielle. Conversation avec Jovino Santos Neto. Jovino Santos Neto a été le pianiste du groupe d’Hermeto Pascoal de 1977 à 1992. Depuis, il estresté le dépositaire informel du patrimoine artistique de ce grand musicien brésilien. A […]
By William Teixeira, Marco Fiorini, Mikhail Malt, Gérard Assayag Musica Hodie, 2024, 24, ⟨10.5216/mh.v24.78611⟩DOI : 10.5216/mh.v24.78611 Read full publication. Abstract: This article details the development of a computational patch designed for real-time processing in the composition of Chronos IIIc, originally written by Brazilian composer Roberto Victório for solo cello. In this version, the piece incorporates […]
Great encounters in IRCAM’s Studio 5 with George Lewis, Gérard Assayag, Marco Fiorini, Damon Holzborn and Hongshuo Fan talking about music technology, improvisation, composition and thinking about new interaction strategies between Voyager and Somax2. George Lewis will be part of the REACH team for the upcoming year, and we cannot wait to see what we […]
