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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper proposes MP-SENet, a novel Speech Enhancement Network whichdirectly denoises Magnitude and Phase spectra in parallel. The proposedMP-SENet adopts a codec architecture in which the encoder and decoder arebridged by convolution-augmented transformers. The encoder aims to encodetime-frequency representations from the input noisy magnitude and phasespectra. The decoder is composed of parallel magnitude mask decoder and phasedecoder, directly recovering clean magnitude spectra and clean-wrapped phasespectra by incorporating learnable sigmoid activation and parallel phaseestimation architecture, respectively. Multi-level losses defined on magnitudespectra, phase spectra, short-time complex spectra, and time-domain waveformsare used to train the MP-SENet model jointly. Experimental results show thatour proposed MP-SENet achieves a PESQ of 3.50 on the public VoiceBank+DEMANDdataset and outperforms existing advanced speech enhancement methods.

MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra