Skip to Main content Skip to Navigation

Separake: Source Separation with a Little Help From Echoes

Robin Scheibler 1 Diego Di Carlo 2 Antoine Deleforge 3, 2 Ivan Dokmanić 4
2 PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
3 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : It is commonly believed that multipath hurts various audio processing algorithms. At odds with this belief, we show that multipath in fact helps sound source separation, even with very simple propagation models. Unlike most existing methods, we neither ignore the room impulse responses, nor we attempt to estimate them fully. We rather assume that we know the positions of a few virtual microphones generated by echoes and we show how this gives us enough spatial diversity to get a performance boost over the anechoic case. We show improvements for two standard algorithms---one that uses only magnitudes of the transfer functions, and one that also uses the phases. Concretely, we show that multichannel non-negative matrix factorization aided with a small number of echoes beats the vanilla variant of the same algorithm, and that with magnitude information only, echoes enable separation where it was previously impossible.
Document type :
Conference papers
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/hal-01909531
Contributor : Antoine Deleforge <>
Submitted on : Tuesday, December 4, 2018 - 3:32:56 PM
Last modification on : Tuesday, February 25, 2020 - 8:08:11 AM
Document(s) archivé(s) le : Tuesday, March 5, 2019 - 12:22:28 PM

File

main.pdf
Files produced by the author(s)

Identifiers

Citation

Robin Scheibler, Diego Di Carlo, Antoine Deleforge, Ivan Dokmanić. Separake: Source Separation with a Little Help From Echoes. ICASSP 2018 - IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Canada. pp.6897-6901, ⟨10.1109/ICASSP.2018.8461345⟩. ⟨hal-01909531⟩

Share

Metrics

Record views

217

Files downloads

160