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

Representation learning from unlabeled data has been of major interest inartificial intelligence research. While self-supervised speech representationlearning has been popular in the speech research community, very few works havecomprehensively analyzed audio representation learning for non-speech audiotasks. In this paper, we propose a self-supervised audio representationlearning method and apply it to a variety of downstream non-speech audio tasks.We combine the well-known wav2vec 2.0 framework, which has shown success inself-supervised learning for speech tasks, with parameter-efficient conformerarchitectures. Our self-supervised pre-training can reduce the need for labeleddata by two-thirds. On the AudioSet benchmark, we achieve a mean averageprecision (mAP) score of 0.415, which is a new state-of-the-art on this datasetthrough audio-only self-supervised learning. Our fine-tuned conformers alsosurpass or match the performance of previous systems pre-trained in asupervised way on several downstream tasks. We further discuss the importantdesign considerations for both pre-training and fine-tuning.

Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks