Distribution Preserving Source Separation With Time Frequency Predictive Models
arXiv:2303.05896 · doi:10.23919/EUSIPCO58844.2023.10290022
Abstract
We provide an example of a distribution preserving source separation method, which aims at addressing perceptual shortcomings of state-of-the-art methods. Our approach uses unconditioned generative models of signal sources. Reconstruction is achieved by means of mix-consistent sampling from a distribution conditioned on a realization of a mix. The separated signals follow their respective source distributions, which provides an advantage when separation results are evaluated in a listening test.
5 pages, 4 figures, pre-review version submitted to EUSIPCO 2023
References in corpus (8)
- WaveNet: A Generative Model for Raw Audio
- Score-Based Generative Modeling through Stochastic Differential Equations
- Objective Measures of Perceptual Audio Quality Reviewed: An Evaluation of Their Application Domain Dependence
- Multi-instrument Music Synthesis with Spectrogram Diffusion
- Multi-Source Diffusion Models for Simultaneous Music Generation and Separation
- CRASH: Raw Audio Score-based Generative Modeling for Controllable High-resolution Drum Sound Synthesis
- On tuning consistent annealed sampling for denoising score matching
- Music Separation Enhancement with Generative Modeling