MULTICHANNEL AUDIO SOURCE SEPARATION WITH PROBABILISTIC REVERBERATION MODELING

Abstract : In this paper we show that considering early contributions of mixing filters through a probabilistic prior can help blind source separation in reverberant recording conditions. By modeling mixing filters as the direct path plus R−1 reflections, we represent the propagation from a source to a mixture channel as an autoregressive process of order R in the frequency domain. This model is used as a prior to derive a Maximum A Posteriori (MAP) estimation of the mixing filters using the Expectation-Maximization (EM) algorithm. Experimental results over reverberant synthetic mixtures and live recordings show that MAP estimation with this prior provides better separation results than a Maximum Likelihood (ML) estimation.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01219635
Contributor : Roland Badeau <>
Submitted on : Friday, October 23, 2015 - 12:00:59 AM
Last modification on : Thursday, October 17, 2019 - 12:36:09 PM
Long-term archiving on : Friday, April 28, 2017 - 6:57:28 AM

File

Leglaive-WASPAA-2015.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01219635, version 1

Collections

Citation

Simon Leglaive, Roland Badeau, Gaël Richard. MULTICHANNEL AUDIO SOURCE SEPARATION WITH PROBABILISTIC REVERBERATION MODELING. Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Oct 2015, New Paltz, NY, United States. pp.5. ⟨hal-01219635⟩

Share

Metrics

Record views

238

Files downloads

309