Gérard Assayag, Laurent Bonnasse-Gahot, Joakim Borg; Cocreative Interaction: Somax2 and the REACH Project. Computer Music Journal 2022; 46 (4): 7–25. doi: https://doi.org/10.1162/comj_a_00662 https://direct.mit.edu/comj/issue/46/4 Abstract : Somax2 is an artificial intelligence (AI)-based multiagent system for human–machine “coimprovisation” that generates stylistically coherent streams while continuously listening and adapting to musicians or other agents. The model on which it is based can be […]
Publications
A.I. KOMBOÏ: RE-IMAGINING XENAKIS’ KOMBOÏ THROUGH CYBER-HUMAN CO-CREATIVE IMPROVISATION PRACTICE
Article by Marco Fiorini (IRCAM, REACH) and Lorenzo Colombo (DKDM, the Royal Danish Academy of Music) has been accepted for the JIM2024 conference (Journées d’Informatique Musicale, 6-8 May 2024, Marseille, France). Read the full paper Watch the video of the performance RésuméDans cet article, nous documentons une recherche artistique et scientifique dans laquelle nous réimaginons […]
Xenakis Komboï Reloaded by Somax2
Marco Fiorini: Somax2 interactive AI Lorenzo Colombo: percussion Recorded at the Royal Danish Academy of Music on June 6th 2023 at KLANG festival in Copenhagen
Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation
Read full publication. Published by Yusong Wu, Ke Chen, Tianyu Zhang, Yuchen Hui, Marianna Nezhurina, Taylor Berg-Kirkpatrick, Shlomo Dubnov. Abstract: Contrastive learning has shown remarkable success in the field of multimodal representation learning. In this paper, we propose a pipeline of contrastive language-audio pretraining to develop an audio representation by combining audio data with natural […]
Challenging epistemic biases in musical AI: a guerrilla approach to human – machine comprovisation based on Xenakis’s sketches for Evryali
Article by Pavlos Antoniadis, Department of Music Studies, University of Ioannina. Download article Abstract: The objective of this paper is to reflect on the affordances of sketches as interfaces for human and machine learning, by way of a case-study based on Iannis Xenakis’s Evryali (1973). First, we report on one-to-one mappings between the composer’s original […]
Mathematical Morphology for the Analysis and Generation of Time-Frequency Representations of Music
Gonzalo Romero-García. Mathematical Morphology for the Analysis and Generation of TimeFrequency Representations of Music. Signal and Image Processing. Sorbonne Université, 2023. English. ffNNT : 2023SORUS554ff. fftel-04470770f Full publication Download publication Abstract: This thesis explores the application of Mathematical Morphology to the analysis and generation of music, focusing on two time-frequency representations: spectrograms and piano rolls. […]
Evaluating Co-Creativity using Total Information Flow
Read full publication. Published by Vignesh Gokul, Chris Francis, Shlomo Dubnov. Abstract: Co-creativity in music refers to two or more musicians or musical agents interacting with one another by composing or improvising music. However, this is a very subjective process and each musician has their own preference as to which improvisation is better for some […]
Discovering Repeated Patterns From the Onsets in a Multidimensional Representation of Music
Paul Lascabettes & Isabelle Bloch. Discovering Repeated Patterns from Onsets, Third International Conference on Discrete Geometry and Mathematical Morphology, (DGMM), Firenze, Italy, accepted. Full publication Download publication Abstract: This article deals with the discovery of repeated patterns in a multidimensional representation of music using the theory of mathematical morphology. The main idea proposed here is […]
Binaural sound source localization using a hybrid time and frequency domain model
Gil Geva, Binaural sound source localization using a hybrid time and frequency domain model, Master Reichman University, Sept 2023 (direction S. Dubnov, O. Warusfel,G. Assayag) Full publication Download publication Abstract: This paper introduces a new approach to sound source localization using head-related transfer function (HRTF) characteristics, which enable precise full-sphere localization from raw data. While […]
Cocreative Interaction: Somax2 and the REACH Project
Full publication By Gérard Assayag, Laurent Bonnasse-Gahot, Joakim Borg Abstract: Somax2 is an artificial intelligence (AI)-based multiagent system for human–machine co-improvisation that generates stylistically coherent streams while continuously listening and adapting to musicians or other agents. The model on which it is based can be used with little configuration to interact with humans in full autonomy, […]