Article by Marco Fiorini (IRCAM, Sorbonne Université, CNRS) and Nicolas Brochec (Tokyo University of the Arts) has been accepted for the SMC2024 conference (Sound and Music Computing, 4-6 July 2024, Porto, Portugal).
Watch a video demo of the system
Abstract: This paper presents a novel application and integration of a state-of-the-art CNN-based classifier for real-time flute Instrumental Playing Technique (IPT) recognition within the co-creative system Somax2. Focusing on music innovation in the framework of Corpus-Based Concatenative Synthesis (CBCS), our work addresses the critical gap of recognising instantaneous changes in instrumental playing techniques during co-improvisation with artificial agents. Our real-time IPT recognition system offers a new dimension to the Somax2 interaction paradigm, where artificial agents are now able to responsively engage with the recognized techniques.
Contributing to the broader field of human-machine interaction in computer music, our results have potential applications in improvisation, computer-aided composition and new interfaces for musical expression.
