Online Spectrogram Inversion for Low-Latency Audio Source Separation - Archive ouverte HAL Access content directly
Journal Articles IEEE Signal Processing Letters Year : 2020

Online Spectrogram Inversion for Low-Latency Audio Source Separation

(1) , (2)
Paul Magron
  • Function : Author
  • PersonId : 1085197
Tuomas Virtanen
  • Function : Author
  • PersonId : 1113848


Audio source separation is usually achieved by estimating the short-time Fourier transform (STFT) magnitude of each source, and then applying a spectrogram inversion algorithm to retrieve time-domain signals. In particular, the multiple input spectrogram inversion (MISI) algorithm has been exploited successfully in several recent works. However, this algorithm suffers from two drawbacks, which we address in this paper. First, it has originally been introduced in a heuristic fashion: we propose here a rigorous optimization framework in which MISI is derived, thus proving the convergence of this algorithm. Besides, while MISI operates offline, we propose here an online version of MISI called oMISI, which is suitable for low-latency source separation, an important requirement for e.g., hearing aids applications. oMISI also allows one to use alternative phase initialization schemes exploiting the temporal structure of audio signals. Experiments conducted on a speech separation task show that oMISI performs as well as its offline counterpart, thus demonstrating its potential for real-time source separation.
Fichier principal
Vignette du fichier
Online_MISI.pdf (525.72 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03132170 , version 1 (11-10-2021)



Paul Magron, Tuomas Virtanen. Online Spectrogram Inversion for Low-Latency Audio Source Separation. IEEE Signal Processing Letters, 2020, 27, pp.306-310. ⟨10.1109/LSP.2020.2970310⟩. ⟨hal-03132170⟩
130 View
41 Download



Gmail Facebook Twitter LinkedIn More