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/

Zendy Plus

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

Zendy Tools

Zendy Open

Recent studies have shown that neural vocoders based on generativeadversarial network (GAN) can generate audios with high quality. While GANbased neural vocoders have shown to be computationally much more efficient thanthose based on autoregressive predictions, the real-time generation of thehighest quality audio on CPU is still a very challenging task. One majorcomputation of all GAN-based neural vocoders comes from the stacked upsamplinglayers, which were designed to match the length of the waveform's length ofoutput and temporal resolution. Meanwhile, the computational complexity ofupsampling networks is closely correlated with the numbers of samples generatedfor each window. To reduce the computation of upsampling layers, we propose anew GAN based neural vocoder called Basis-MelGAN where the raw audio samplesare decomposed with a learned basis and their associated weights. As theprediction targets of Basis-MelGAN are the weight values associated with eachlearned basis instead of the raw audio samples, the upsampling layers inBasis-MelGAN can be designed with much simpler networks. Compared with otherGAN based neural vocoders, the proposed Basis-MelGAN could produce comparablehigh-quality audio but significantly reduced computational complexity fromHiFi-GAN V1's 17.74 GFLOPs to 7.95 GFLOPs.

Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition