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

Few-shot learning aims to train models that can recognize novel classes givenjust a handful of labeled examples, known as the support set. While the fieldhas seen notable advances in recent years, they have often focused onmulti-class image classification. Audio, in contrast, is often multi-label dueto overlapping sounds, resulting in unique properties such as polyphony andsignal-to-noise ratios (SNR). This leads to unanswered questions concerning theimpact such audio properties may have on few-shot learning system design,performance, and human-computer interaction, as it is typically up to the userto collect and provide inference-time support set examples. We address thesequestions through a series of experiments designed to elucidate the answers tothese questions. We introduce two novel datasets, FSD-MIX-CLIPS andFSD-MIX-SED, whose programmatic generation allows us to explore these questionssystematically. Our experiments lead to audio-specific insights on few-shotlearning, some of which are at odds with recent findings in the image domain:there is no best one-size-fits-all model, method, and support set selectioncriterion. Rather, it depends on the expected application scenario. Our codeand data are available at https://github.com/wangyu/rethink-audio-fsl.

Who calls the shots? Rethinking Few-Shot Learning for Audio