Marco Fiorini, Mikhail Malt. Somax2 – A Distributed Co-Creative System for Human-Machine Co-Improvisation. Proceedings of the Second International Conference on Hybrid Human-Artificial Intelligence HHAI 2023, Jun 2023, Munich, Germany. ⟨hal-04444997⟩ Full publication Download PDF Abstract: Somax2 is a multi-agent interactive system, based on machine-listening, machine learning and generative units, performing live machine co-improvisation with musicians. […]
Somax2 workshop presentation at festival ManiFeste Academie 2023 at IRCAM, by Marco Fiorini (REACH).
avec Mikhail Malt, chercheur à l’Ircam-STMS et Marco Fiorini, doctorant à l’Ircam-STMS. Après une brève présentation du fonctionnement de l’environnement Somax2, nous vous proposerons une réflexion en action des sujets de la performance, du contrôle et de l’instrumentalisé dans le cadre de l’utilisation d’algorithmes d’I.A. en improvisation musicale. Nous questionnerons notamment le cas non idiomatique en musique […]
Marco Fiorini, Improvised Musical Interaction with Creative Agents, Aalborg University Copenhagen, Juin 2023 Full publication Download publication Abstract: This thesis was written as the final project of the Master of Science in Sound and Music Computing at Aalborg University Copenhagen. The presented work has been carried out in the Music Representations team at IRCAM – […]
Read full publication. Published by Hao-Wen Dong, Ke Chen, Shlomo Dubnov, Julian McAuley, Taylor Berg-Kirkpatrick. Abstract: Existing approaches for generating multitrack music with transformer models have been limited in terms of the number of instruments, the length of the music segments and slow inference. This is partly due to the memory requirements of the lengthy […]
Marc Chemillier (CAMS-EHESS), Yohann Rabearivelo (CAMS-EHESS), Rémi Jaylet (Télécom Paris), contact: chemilli@ehess.fr Read full publication Abstract: In this paper we present a research dealing with musical improvisation practices on TikTok as part of a project devoted to the development of a music improvisation software. Finding musicians to experiment with led us to explore the musical collaborations […]
Yusong Wu, K. Chen, T. Zhang, Y. Hui, T. Berg-Kirkpatrick and S. Dubnov, « Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation, » ICASSP 2023 – 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.10095969. Full publication Abstract: Contrastive learning has shown remarkable success in the […]
HAo-Wen Dong, K. Chen, S. Dubnov, J. McAuley and T. Berg-Kirkpatrick, « Multitrack Music Transformer, » ICASSP 2023 – 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.10094628. Full publication Abstract: Existing approaches for generating multitrack music with transformer models have been limited in terms of the […]
Improtech aura lieu à Uzeste du 11 au 13 août 2023. Après des éditions remarquées à New York, Philadelphie et Athènes, Improtech @ Uzeste ! (ikUzeste’23) se tiendra du 11 au 13 août 2023 à Uzeste, le beau village occitan où se déroule la mythique Hestajada de les arts, le festival de musique fondé par Bernard […]
Presented during the IRCAM Forum Workshop 2023 In Paris by Mikhail Malt and Marco Fiorini. Somax 2.5 is an application and a library for live co-creative interaction with musicians in improvisation composition or installation scenarios. It is based on a machine listening, reactive engine and generative model that provide stylistically coherent improvisation while continuously adapting […]
