User-guided one-shot deep model adaptation for music source separation - Télécom Paris Access content directly
Conference Papers Year : 2021

User-guided one-shot deep model adaptation for music source separation

Abstract

Music source separation is the task of isolating individual instruments which are mixed in a musical piece. This task is particularly challenging, and even state-of-the-art models can hardly generalize to unseen test data. Nevertheless, prior knowledge about individual sources can be used to better adapt a generic source separation model to the observed signal. In this work, we propose to exploit a temporal segmentation provided by the user, that indicates when each instrument is active, in order to fine-tune a pre-trained deep model for source separation and adapt it to one specific mixture. This paradigm can be referred to as user-guided one-shot deep model adaptation for music source separation, as the adaptation acts on the target song instance only. Our results are promising and show that state-of-the-art source separation models have large margins of improvement especially for those instruments which are underrepresented in the training data.
Fichier principal
Vignette du fichier
UGOSA_Hal.pdf (3.17 Mo) Télécharger le fichier
UGOSA_slides_1610.pdf (4.71 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03219350 , version 1 (06-05-2021)
hal-03219350 , version 2 (02-06-2021)
hal-03219350 , version 3 (29-07-2021)

Identifiers

  • HAL Id : hal-03219350 , version 3

Cite

Giorgia Cantisani, Alexey Ozerov, Slim Essid, Gael Richard. User-guided one-shot deep model adaptation for music source separation. 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), IEEE, Oct 2021, New Paltz, NY, United States. ⟨hal-03219350v3⟩
484 View
637 Download

Share

Gmail Facebook X LinkedIn More