Advances in audio source separation and multisource audio content retrieval

Emmanuel Vincent 1
1 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Audio source separation aims to extract the signals of individual sound sources from a given recording. In this paper, we review three recent advances which improve the robustness of source separation in real-world challenging scenarios and enable its use for multisource content retrieval tasks, such as automatic speech recognition (ASR) or acoustic event detection (AED) in noisy environments. We present a Flexible Audio Source Separation Toolkit (FASST) and discuss its advantages compared to earlier approaches such as independent component analysis (ICA) and sparse component analysis (SCA). We explain how cues as diverse as harmonicity, spectral envelope, temporal fine structure or spatial location can be jointly exploited by this toolkit. We subsequently present the uncertainty decoding (UD) framework for the integration of audio source separation and audio content retrieval. We show how the uncertainty about the separated source signals can be accurately estimated and propagated to the features. Finally, we explain how this uncertainty can be efficiently exploited by a classifier, both at the training and the decoding stage. We illustrate the resulting performance improvements in terms of speech separation quality and speaker recognition accuracy.
Liste complète des métadonnées

Cited literature [10 references]  Display  Hide  Download

https://hal.inria.fr/hal-00664090
Contributor : Emmanuel Vincent <>
Submitted on : Monday, February 27, 2012 - 9:50:37 AM
Last modification on : Thursday, March 21, 2019 - 2:20:12 PM
Document(s) archivé(s) le : Thursday, June 14, 2012 - 4:27:57 PM

File

vincent_DSS12.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00664090, version 1

Citation

Emmanuel Vincent. Advances in audio source separation and multisource audio content retrieval. 2012. ⟨hal-00664090⟩

Share

Metrics

Record views

424

Files downloads

228