Conferences Workshops

Performance, contrôle et instrumentalité dans 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 […]

Publications

Multitrack music transformer

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 […]

Publications

Observing Musical Communities Dedicated to Improvisation and Duet Practice on TikTok Using Web Scraping

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 […]

Conferences Publications

Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation

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 […]

Conferences Publications

Multitrack Music Transformer

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 […]

Conferences Workshops

News on Somax version 2.5

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 […]

Publications

Switching Machine Improvisation Models by Latent Transfer Entropy Criteria

Shlomo Dubnov, Vignesh Gokul, Gérard Assayag. Switching Machine Improvisation Models by Latent Transfer Entropy Criteria. Physical Sciences Forum, 2023, 5 (1), pp.49. ff10.3390/psf2022005049ff.ffhal-04010744 Full publication Abstract: Music improvisation is the ability of musical generative systems to interact with either another music agent or a human improviser. This is a challenging task, as it is not trivial […]