Skip to Main content Skip to Navigation

Echo-aware signal processing for audio scene analysis: The Call of Echo

Abstract : Most of audio signal processing methods regard reverberation and in particular acoustic echoes as a nuisance. However, they convey important spatial and semantic information about sound sources and, based on this, recent echo-aware methods have been proposed. In this work, we focus on two directions. First, we study how to estimate acoustic echoes blindly from microphone recordings. Two approaches are proposed, one leveraging on continuous dictionaries, one using recent deep learning techniques. Then, we focus on extending existing methods in audio scene analysis to their echo-aware forms. The Multichannel NMF framework for audio source separation, the SRP-PHAT localization method, and the MVDR beamformer for speech enhancement are all extended to their echo-aware versions.
Complete list of metadata
Contributor : Diego Di Carlo Connect in order to contact the contributor
Submitted on : Friday, February 5, 2021 - 7:31:25 PM
Last modification on : Saturday, February 13, 2021 - 3:27:12 AM
Long-term archiving on: : Friday, May 7, 2021 - 8:29:10 AM


Files produced by the author(s)


  • HAL Id : tel-03133271, version 1


Diego Di Carlo. Echo-aware signal processing for audio scene analysis: The Call of Echo. Signal and Image processing. UNIVERSITÉ DE RENNES 1; INRIA - IRISA - PANAMA, 2020. English. ⟨tel-03133271v1⟩



Record views


Files downloads