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

Entertainment-oriented singing voice synthesis (SVS) requires a vocoder togenerate high-fidelity (e.g. 48kHz) audio. However, most text-to-speech (TTS)vocoders cannot reconstruct the waveform well in this scenario. In this paper,we propose HiFi-WaveGAN to synthesize the 48kHz high-quality singing voices inreal-time. Specifically, it consists of an Extended WaveNet served as agenerator, a multi-period discriminator proposed in HiFiGAN, and amulti-resolution spectrogram discriminator borrowed from UnivNet. To betterreconstruct the high-frequency part from the full-band mel-spectrogram, weincorporate a pulse extractor to generate the constraint for the synthesizedwaveform. Additionally, an auxiliary spectrogram-phase loss is utilized toapproximate the real distribution further. The experimental results show thatour proposed HiFi-WaveGAN obtains 4.23 in the mean opinion score (MOS) metricfor the 48kHz SVS task, significantly outperforming other neural vocoders.

HiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation