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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Contrastive Language-Audio Pretraining (CLAP) became of crucial importance inthe field of audio and speech processing. Its employment ranges from soundevent detection to text-to-audio generation. However, one of the mainlimitations is the considerable amount of data required in the training processand the overall computational complexity during inference. This paperinvestigates how we can reduce the complexity of contrastive language-audiopre-trained models, yielding an efficient model that we call tinyCLAP. Wederive an unimodal distillation loss from first principles and explore how thedimensionality of the shared, multimodal latent space can be reduced viapruning. TinyCLAP uses only 6% of the original Microsoft CLAP parameters with aminimal reduction (less than 5%) in zero-shot classification performance acrossthe three sound event detection datasets on which it was tested

tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models