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

Transformers have become central to recent advances in audio classification.However, training an audio spectrogram transformer, e.g. AST, from scratch canbe resource and time-intensive. Furthermore, the complexity of transformersheavily depends on the input audio spectrogram size. In this work, we aim tooptimize AST training by linking to the resolution in the time-axis. Weintroduce multi-phase training of audio spectrogram transformers by connectingthe seminal idea of coarse-to-fine with transformer models. To achieve this, wepropose a set of methods for temporal compression. By employing one of thesemethods, the transformer model learns from lower-resolution (coarse) data inthe initial phases, and then is fine-tuned with high-resolution data later in acurriculum learning strategy. Experimental results demonstrate that theproposed training mechanism for AST leads to improved (or on-par) performancewith faster convergence, i.e. requiring fewer computational resources and lesstime. This approach is also generalizable to other AST-based methods regardlessof their learning paradigms.

From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers