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

In text-audio retrieval (TAR) tasks, due to the heterogeneity of contentsbetween text and audio, the semantic information contained in the text is onlysimilar to certain frames within the audio. Yet, existing works aggregate theentire audio without considering the text, such as mean-pooling over theframes, which is likely to encode misleading audio information not described inthe given text. In this paper, we present a text-aware attention pooling (TAP)module for TAR, which is essentially a scaled dot product attention for a textto attend to its most semantically similar frames. Furthermore, previousmethods only conduct the softmax for every single-side retrieval, ignoring thepotential cross-retrieval information. By exploring the intrinsic prior of eachtext-audio pair, we introduce a prior matrix revised (PMR) loss to filter thehard case with high (or low) text-to-audio but low (or high) audio-to-textsimilarity scores, thus achieving the dual optimal match. Experiments show thatour TAP significantly outperforms various text-agnostic pooling functions.Moreover, our PMR loss also shows stable performance gains on multipledatasets.

Improving Text-Audio Retrieval by Text-aware Attention Pooling and Prior Matrix Revised Loss