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

High-quality speech corpora are essential foundations for most speechapplications. However, such speech data are expensive and limited since theyare collected in professional recording environments. In this work, we proposean encoder-decoder neural network to automatically enhance low-qualityrecordings to professional high-quality recordings. To address channelvariability, we first filter out the channel characteristics from the originalinput audio using the encoder network with adversarial training. Next, wedisentangle the channel factor from a reference audio. Conditioned on thisfactor, an auto-regressive decoder is then used to predict thetarget-environment Mel spectrogram. Finally, we apply a neural vocoder tosynthesize the speech waveform. Experimental results show that the proposedsystem can generate a professional high-quality speech waveform when settinghigh-quality audio as the reference. It also improves speech enhancementperformance compared with several state-of-the-art baseline systems.

Enhancing Low-Quality Voice Recordings Using Disentangled Channel Factor and Neural Waveform Model