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

We present a new Self-Supervised Learning (SSL) approach to pre-trainencoders on unlabeled audio data that reduces the need for large amounts oflabeled data for audio and speech classification. Our primary aim is to learnaudio representations that can generalize across a large variety of speech andnon-speech tasks in a low-resource un-labeled audio pre-training setting.Inspired by the recent success of clustering and contrasting learning paradigmsfor SSL-based speech representation learning, we propose SLICER (SymmetricalLearning of Instance and Cluster-level Efficient Representations), which bringstogether the best of both clustering and contrasting learning paradigms. We usea symmetric loss between latent representations from student and teacherencoders and simultaneously solve instance and cluster-level contrastivelearning tasks. We obtain cluster representations online by just projecting theinput spectrogram into an output subspace with dimensions equal to the numberof clusters. In addition, we propose a novel mel-spectrogram augmentationprocedure, k-mix, based on mixup, which does not require labels and aidsunsupervised representation learning for audio. Overall, SLICER achievesstate-of-the-art results on the LAPE Benchmark \cite{9868132}, significantlyoutperforming DeLoRes-M and other prior approaches, which are pre-trained on$10\times$ larger of unsupervised data. We will make all our codes available onGitHub.

SLICER: Learning universal audio representations using low-resource self-supervised pre-training