@article{634464df513449ceb61db04daedf2e92,
author = " Paul Magron and Tuomas Virtanen",
abstract = "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 letter. 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.",
doi = "10.1109/LSP.2020.2970310",
issn = "1070-9908",
journal = "IEEE Signal Processing Letters",
keywords = "Audio source separation; low-latency; online spectrogram inversion; phase recovery; sinusoidal modeling",
pages = "306--310",
publisher = "Institute of Electrical and Electronics Engineers",
title = "{O}nline {S}pectrogram {I}nversion for {L}ow-{L}atency {A}udio {S}ource {S}eparation",
volume = "27",
year = "2020",
}