Share Email Print
cover

Proceedings Paper

Advances in audio source seperation and multisource audio content retrieval
Author(s): Emmanuel Vincent
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 10 May 2012
PDF: 6 pages
Proc. SPIE 8401, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X, 840109 (10 May 2012); doi: 10.1117/12.926411
Show Author Affiliations
Emmanuel Vincent, INRIA, Ctr. de Rennes - Bretagne Atlantique (France)


Published in SPIE Proceedings Vol. 8401:
Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X
Harold Szu, Editor(s)

© SPIE. Terms of Use
Back to Top