Publications

Improving Generalization of Speech Separation in Real-World Scenarios: Strategies in Simulation, Optimization, and Evaluation

View original. Published by Ke Chen, Jiaqi Su, Taylor Berg-Kirkpatrick, Shlomo Dubnov, Zeyu Jin. Abstract: Achieving robust speech separation for overlapping speakers in various acoustic environments with noise and reverberation remains an open challenge. Although existing datasets are available to train separators for specific scenarios, they do not effectively generalize across diverse real-world scenarios. In […]

Residences Workshops

Artistic Residence Valérie Philippin & Mikhail Malt

Restitution de la résidence de recherche artistique, de Valérie Philippin et Mikhail Malt, dans le cadre du projet REACH et présentation de Somax2 full video at https://medias.ircam.fr/x77ccfb_presentation-et-module-applicatif-suite-a In 2023, Mikhail Malt invited Valérie Philippin to a creative research residency at Ircam during the 2023-24 season, to develop Somax2 around the (re)composition of speech and create […]

Publications

Retrieval Guided Music Captioning via Multimodal Prefxes

Read full publication. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24)Special Track on AI, the Arts and Creativity. Published by Nikita Srivatsan, Ke Chen, Shlomo Dubnov and Taylor Berg-Kirkpatrick. Abstract: In this paper we put forward a new approach to music captioning, the task of automatically generating natural language descriptions for songs. […]

Concerts Conferences Events

Improtech Paris – Tokyo is over.

Improtech is a musical festival and an interdisciplinary workshop bringing together research and creation in musician – machine intelligent musical interaction. After praised editions in New York, Philadelphia, Athens and Uzeste, Improtech Paris-Tokyo has landed down in Tokyo, on july 29, 2024, organised by REACH. This edition of Improtech in Tokyo has welcomed a number of brillant personalities during a week long […]

Publications

Musicldm: Enhancing novelty in text-to-music generation using beat-synchronous mixup strategies

Read full publication. Published by Ke Chen, Yusong Wu, Haohe Liu, Marianna Nezhurina, Taylor Berg-Kirkpatrick, Shlomo Dubnov. Abstract: Diffusion models have shown promising results in cross-modal generation tasks, including text-to-image and text-to-audio generation. However, generating music, as a special type of audio, presents unique challenges due to limited availability of music data and sensitive issues […]

Publications

Microphone-based Data Augmentation for Automatic Recognition of Instrumental Playing Techniques

Paper written by Nicolas Brochec*, Tsubasa Tanaka*, and Will Howie*† has been presented at the ICMC2024 (International Computer Music Conference 2024). * Tokyo University of the Arts† Japan Society for the Promotion of Science Full publication Abstract: Within existing research on the automatic classification of musical instrument playing techniques, few available datasets include enough playing […]

Publications

Maths & Musique #3 : Musique, combinatoire des mots et improvisation par ordinateur, par Marc Chemillier

Lire la publication originale. Par Marc Chemillier, Directeur d’études de l’EHESS La musique entretient depuis toujours des liens étroits avec les mathématiques. Les pythagoriciens à partir du Ve siècle avant J.-C. commencent à s’intéresser aux rapports entre la musique et les nombres. Beaucoup plus proche de nous, Joseph Fourier (1768-1830) jette les bases de l’analyse harmonique […]