DMCA
Probabilistic modeling paradigms for audio source separation (2010)
| Venue: | In Machine Audition: Principles, Algorithms and Systems. IGI Global |
| Citations: | 25 - 14 self |
BibTeX
@INPROCEEDINGS{Vincent10probabilisticmodeling,
author = {Emmanuel Vincent and Maria G. Jafari and Samer A. Abdallah and Mark D. Plumbley and Mike E. Davies},
title = {Probabilistic modeling paradigms for audio source separation},
booktitle = {In Machine Audition: Principles, Algorithms and Systems. IGI Global},
year = {2010}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Most sound scenes result from the superposition of several sources, which can be separately perceived and analyzed by human listeners. Source separation aims to provide machine listeners with similar skills by extracting the sounds of individual sources from a given scene. Existing separation systems operate either by emulating the human auditory system or by inferring the parameters of probabilistic sound models. In this chapter, we focus on the latter approach and provide a joint overview of established and recent models, including independent component analysis, local time-frequency models and spectral template-based models. We show that most models are instances of one of the following two general paradigms: linear modeling or variance modeling. We compare the merits of either paradigm and report objective performance figures. We conclude by discussing promising combinations of probabilistic priors and inference algorithms that could form the basis of future state-of-the-art systems.
Keyphrases
audio source separation probabilistic modeling paradigm several source independent component analysis source separation machine listener probabilistic sound model future state-of-the-art system similar skill latter approach individual source variance modeling human listener linear modeling recent model promising combination report objective performance figure sound scene result local time-frequency model separation system probabilistic prior inference algorithm joint overview spectral template-based model human auditory system general paradigm
