HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes

Nicolas Furnon 1 Romain Serizel 1 Slim Essid 2 Irina Illina 1
1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : Speech enhancement promises higher efficiency in ad-hoc microphone arrays than in constrained microphone arrays thanks to the wide spatial coverage of the devices in the acoustic scene. However, speech enhancement in ad-hoc microphone arrays still raises many challenges. In particular, the algorithms should be able to handle a variable number of microphones, as some devices in the array might appear or disappear. In this paper, we propose a solution that can efficiently process the spatial information captured by the different devices of the microphone array, while being robust to a link failure. To do this, we use an attention mechanism in order to put more weight on the relevant signals sent throughout the array and to neglect the redundant or empty channels.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03259801
Contributor : Nicolas Furnon Connect in order to contact the contributor
Submitted on : Monday, June 14, 2021 - 2:43:14 PM
Last modification on : Thursday, May 5, 2022 - 10:29:17 AM
Long-term archiving on: : Thursday, September 16, 2021 - 8:22:39 AM

Files

eusipco2021.pdf
Files produced by the author(s)

Identifiers

Citation

Nicolas Furnon, Romain Serizel, Slim Essid, Irina Illina. Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes. EUSIPCO 2021 - 29th European Signal Processing Conference, IEEE, Aug 2021, Dublin / Virtual, Ireland. ⟨10.23919/EUSIPCO54536.2021.9616358⟩. ⟨hal-03259801⟩

Share

Metrics

Record views

49

Files downloads

58