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

One of the leading single-channel speech separation (SS) models is based on aTasNet with a dual-path segmentation technique, where the size of each segmentremains unchanged throughout all layers. In contrast, our key finding is thatmulti-granularity features are essential for enhancing contextual modeling andcomputational efficiency. We introduce a self-attentive network with a novelsandglass-shape, namely Sandglasset, which advances the state-of-the-art (SOTA)SS performance at significantly smaller model size and computational cost.Forward along each block inside Sandglasset, the temporal granularity of thefeatures gradually becomes coarser until reaching half of the network blocks,and then successively turns finer towards the raw signal level. We also unfoldthat residual connections between features with the same granularity arecritical for preserving information after passing through the bottleneck layer.Experiments show our Sandglasset with only 2.3M parameters has achieved thebest results on two benchmark SS datasets -- WSJ0-2mix and WSJ0-3mix, where theSI-SNRi scores have been improved by absolute 0.8 dB and 2.4 dB, respectively,comparing to the prior SOTA results.

Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation