Hi-Audio, Hybrid and Interpretable Deep neural audio machines, is a European Research Council “Advanced Grant” (AdG) project supported by the European Union’s Horizon 2020 research and innovation program under Grant Agreement-101052978.
Hi-Audio aims to build controllable and frugal machine listening models based on expressive generative modelling and Hybrid deep learning models with application to audio scene analysis, music information retrieval and sound transformation and synthesis.
An example of Hybrid deep learning for audio source separation from K. Schulze-Forster, G. Richard, L. Kelley, C. S. J. Doire and R. Badeau, “Unsupervised Music Source Separation Using Differentiable Parametric Source Models,” in IEEE/ACM Trans. on ASLP, vol. 31, pp. 1276-1289, 2023 (open access)
The project is hosted by IMT (Institut Mines-Telecom) at Telecom Paris, a founding member of Institut polytechnique de Paris.
