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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymagron2023spectrogram

Related papers

• Phase Recovery With Bregman Divergences For Audio Source Separation (2020)0.00
• Mel-spectrogram Inversion Via Alternating Direction Method Of Multipliers (2025)2.26
• Complex NMF Under Phase Constraints Based On Signal Modeling: Application To Audio Source Separation (2016)7.50
• On Ambisonic Source Separation With Spatially Informed Non-negative Tensor Factorization (2025)4.52
• Consep: A Noise- And Reverberation-robust Speech Separation Framework By Magnitude Conditioning (2024)0.00
• Sparse Gaussian Process Audio Source Separation Using Spectrum Priors In The Time-domain (2018)5.84
• Data-driven Source Separation Based On Simplex Analysis (2018)0.00
• Surrogate Source Model Learning For Determined Source Separation (2020)9.59