Spectrogram Inversion for Audio Source Separation via Consistency, Mixing, and Magnitude Constraints - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Spectrogram Inversion for Audio Source Separation via Consistency, Mixing, and Magnitude Constraints

Abstract

Audio source separation is often achieved by estimating the magnitude spectrogram of each source, and then applying a phase recovery (or spectrogram inversion) algorithm to retrieve time-domain signals. Typically, spectrogram inversion is treated as an optimization problem involving one or several terms in order to promote estimates that comply with a consistency property, a mixing constraint, and/or a target magnitude objective. Nonetheless, it is still unclear which set of constraints and problem formulation is the most appropriate in practice. In this paper, we design a general framework for deriving spectrogram inversion algorithm, which is based on formulating optimization problems by combining these objectives either as soft penalties or hard constraints. We solve these by means of algorithms that perform alternating projections on the subsets corresponding to each objective/constraint. Our framework encompasses existing techniques from the literature as well as novel algorithms. We investigate the potential of these approaches for a speech enhancement task. In particular, one of our novel algorithms outperforms other approaches in a realistic setting where the magnitudes are estimated beforehand using a neural network.
Fichier principal
Vignette du fichier
Spectrogram_inversion_algorithms_for_source_separation.pdf (309.89 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04015991 , version 1 (06-03-2023)
hal-04015991 , version 2 (17-10-2023)

Identifiers

Cite

Paul Magron, Tuomas Virtanen. Spectrogram Inversion for Audio Source Separation via Consistency, Mixing, and Magnitude Constraints. EUSIPCO 2023, EURASIP, Sep 2023, Helsinki, Finland. ⟨10.48550/arXiv.2303.01864⟩. ⟨hal-04015991v2⟩
47 View
93 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More