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

Speech separation models are used for isolating individual speakers in manyspeech processing applications. Deep learning models have been shown to lead tostate-of-the-art (SOTA) results on a number of speech separation benchmarks.One such class of models known as temporal convolutional networks (TCNs) hasshown promising results for speech separation tasks. A limitation of thesemodels is that they have a fixed receptive field (RF). Recent research inspeech dereverberation has shown that the optimal RF of a TCN varies with thereverberation characteristics of the speech signal. In this work deformableconvolution is proposed as a solution to allow TCN models to have dynamic RFsthat can adapt to various reverberation times for reverberant speechseparation. The proposed models are capable of achieving an 11.1 dB averagescale-invariant signalto-distortion ratio (SISDR) improvement over the inputsignal on the WHAMR benchmark. A relatively small deformable TCN model of 1.3Mparameters is proposed which gives comparable separation performance to largerand more computationally complex models.

Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation