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

We propose Parallel WaveGAN, a distillation-free, fast, and small-footprintwaveform generation method using a generative adversarial network. In theproposed method, a non-autoregressive WaveNet is trained by jointly optimizingmulti-resolution spectrogram and adversarial loss functions, which caneffectively capture the time-frequency distribution of the realistic speechwaveform. As our method does not require density distillation used in theconventional teacher-student framework, the entire model can be easily trained.Furthermore, our model is able to generate high-fidelity speech even with itscompact architecture. In particular, the proposed Parallel WaveGAN has only1.44 M parameters and can generate 24 kHz speech waveform 28.68 times fasterthan real-time on a single GPU environment. Perceptual listening test resultsverify that our proposed method achieves 4.16 mean opinion score within aTransformer-based text-to-speech framework, which is comparative to the bestdistillation-based Parallel WaveNet system.

Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram