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

For supervised speech enhancement, contextual information is important foraccurate spectral mapping. However, commonly used deep neural networks (DNNs)are limited in capturing temporal contexts. To leverage long-term contexts fortracking a target speaker, this paper treats the speech enhancement assequence-to-sequence mapping, and propose a novel monaural speech enhancementU-net structure based on Transformer, dubbed U-Former. The key idea is to modellong-term correlations and dependencies, which are crucial for accurate noisyspeech modeling, through the multi-head attention mechanisms. For this purpose,U-Former incorporates multi-head attention mechanisms at two levels: 1) amulti-head self-attention module which calculate the attention map along bothtime- and frequency-axis to generate time and frequency sub-attention maps forleveraging global interactions between encoder features, while 2) multi-headcross-attention module which are inserted in the skip connections allows a finerecovery in the decoder by filtering out uncorrelated features. Experimentalresults illustrate that the U-Former obtains consistently better performancethan recent models of PESQ, STOI, and SSNR scores.

U-Former: Improving Monaural Speech Enhancement with Multi-head Self and Cross Attention