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

Supervised learning methods have shown effectiveness in estimating spatialacoustic parameters such as time difference of arrival, direct-to-reverberantratio and reverberation time. However, they still suffer from thesimulation-to-reality generalization problem due to the mismatch betweensimulated and real-world acoustic characteristics and the deficiency ofannotated real-world data. To this end, this work proposes a self-supervisedmethod that takes full advantage of unlabeled data for spatial acousticparameter estimation. First, a new pretext task, i.e. cross-channel signalreconstruction (CCSR), is designed to learn a universal spatial acousticrepresentation from unlabeled multi-channel microphone signals. We mask partialsignals of one channel and ask the model to reconstruct them, which makes itpossible to learn spatial acoustic information from unmasked signals andextract source information from the other microphone channel. Anencoder-decoder structure is used to disentangle the two kinds of information.By fine-tuning the pre-trained spatial encoder with a small annotated dataset,this encoder can be used to estimate spatial acoustic parameters. Second, anovel multi-channel audio Conformer (MC-Conformer) is adopted as the encodermodel architecture, which is suitable for both the pretext and downstreamtasks. It is carefully designed to be able to capture the local and globalcharacteristics of spatial acoustics exhibited in the time-frequency domain.Experimental results of five acoustic parameter estimation tasks on bothsimulated and real-world data show the effectiveness of the proposed method. Tothe best of our knowledge, this is the first self-supervised learning method inthe field of spatial acoustic representation learning and multi-channel audiosignal processing.

Self-Supervised Learning of Spatial Acoustic Representation with Cross-Channel Signal Reconstruction and Multi-Channel Conformer