English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Sound sources localization using multichannel signal processing has been asubject of active research for decades. In recent years, the use of deeplearning in audio signal processing has allowed to drastically improveperformances for machine hearing. This has motivated the scientific communityto also develop machine learning strategies for source localizationapplications. In this paper, we present BeamLearning, a multi-resolution deeplearning approach that allows to encode relevant information contained inunprocessed time domain acoustic signals captured by microphone arrays. The useof raw data aims at avoiding simplifying hypothesis that most traditionalmodel-based localization methods rely on. Benefits of its use are shown forrealtime sound source 2D-localization tasks in reverberating and noisyenvironments. Since supervised machine learning approaches require large-sized,physically realistic, precisely labelled datasets, we also developed a fastGPU-based computation of room impulse responses using fractional delays forimage source models. A thorough analysis of the network representation andextensive performance tests are carried out using the BeamLearning network withsynthetic and experimental datasets. Obtained results demonstrate that theBeamLearning approach significantly outperforms the wideband MUSIC and SRP-PHATmethods in terms of localization accuracy and computational efficiency inpresence of heavy measurement noise and reverberation.

BeamLearning: an end-to-end Deep Learning approach for the angular localization of sound sources using raw multichannel acoustic pressure data