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

Speech separation is an important problem in speech processing, which targetsto separate and generate clean speech from a mixed audio containing speech fromdifferent speakers. Empowered by the deep learning technologies oversequence-to-sequence domain, recent neural speech separation models are nowcapable of generating highly clean speech audios. To make these models morepractical by reducing the model size and inference time while maintaining highseparation quality, we propose a new transformer-based speech separationapproach, called TransMask. By fully un-leashing the power of self-attention onlong-term dependency exception, we demonstrate the size of TransMask is morethan 60% smaller and the inference is more than 2 times faster thanstate-of-the-art solutions. TransMask fully utilizes the parallelism duringinference, and achieves nearly linear inference time within reasonable inputaudio lengths. It also outperforms existing solutions on output speech audioquality, achieving SDR above 16 over Librimix benchmark.

TransMask: A Compact and Fast Speech Separation Model Based on Transformer