1 code implementation • 18 Mar 2024 • Emilian Postolache, Giorgio Mariani, Luca Cosmo, Emmanouil Benetos, Emanuele Rodolà
Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separation.
1 code implementation • 13 Nov 2023 • Chin-Yun Yu, Emilian Postolache, Emanuele Rodolà, György Fazekas
In this paper, we examine this problem in the context of duet singing voices separation, and propose a method to enforce the coherency of singer identity by splitting the mixture into overlapping segments and performing posterior sampling in an auto-regressive manner, conditioning on the previous segment.
no code implementations • 23 Oct 2023 • Marco Comunità, Riccardo F. Gramaccioni, Emilian Postolache, Emanuele Rodolà, Danilo Comminiello, Joshua D. Reiss
Sound design involves creatively selecting, recording, and editing sound effects for various media like cinema, video games, and virtual/augmented reality.
3 code implementations • 17 May 2023 • Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca, Michele Mancusi, Riccardo Marin, Emanuele Rodolà
We propose to reframe the standard greedy autoregressive decoding of MT with a parallel formulation leveraging Jacobi and Gauss-Seidel fixed-point iteration methods for fast inference.
1 code implementation • 4 Feb 2023 • Giorgio Mariani, Irene Tallini, Emilian Postolache, Michele Mancusi, Luca Cosmo, Emanuele Rodolà
In this work, we define a diffusion-based generative model capable of both music synthesis and source separation by learning the score of the joint probability density of sources sharing a context.
1 code implementation • 9 Jan 2023 • Emilian Postolache, Giorgio Mariani, Michele Mancusi, Andrea Santilli, Luca Cosmo, Emanuele Rodolà
Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task performance.
no code implementations • 21 Oct 2022 • Emilian Postolache, Jordi Pons, Santiago Pascual, Joan Serrà
Universal sound separation consists of separating mixes with arbitrary sounds of different types, and permutation invariant training (PIT) is used to train source agnostic models that do so.
1 code implementation • 11 Oct 2021 • Michele Mancusi, Emilian Postolache, Giorgio Mariani, Marco Fumero, Andrea Santilli, Luca Cosmo, Emanuele Rodolà
State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling resources.
Ranked #1 on Music Source Separation on Slakh2100