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

End-to-end singing voice synthesis (SVS) model VISinger can achieve betterperformance than the typical two-stage model with fewer parameters. However,VISinger has several problems: text-to-phase problem, the end-to-end modellearns the meaningless mapping of text-to-phase; glitches problem, the harmoniccomponents corresponding to the periodic signal of the voiced segment occurs asudden change with audible artefacts; low sampling rate, the sampling rate of24KHz does not meet the application needs of high-fidelity generation with thefull-band rate (44.1KHz or higher). In this paper, we propose VISinger 2 toaddress these issues by integrating the digital signal processing (DSP) methodswith VISinger. Specifically, inspired by recent advances in differentiabledigital signal processing (DDSP), we incorporate a DSP synthesizer into thedecoder to solve the above issues. The DSP synthesizer consists of a harmonicsynthesizer and a noise synthesizer to generate periodic and aperiodic signals,respectively, from the latent representation z in VISinger. It supervises theposterior encoder to extract the latent representation without phaseinformation and avoid the prior encoder modelling text-to-phase mapping. Toavoid glitch artefacts, the HiFi-GAN is modified to accept the waveformsgenerated by the DSP synthesizer as a condition to produce the singing voice.Moreover, with the improved waveform decoder, VISinger 2 manages to generate44.1kHz singing audio with richer expression and better quality. Experiments onOpenCpop corpus show that VISinger 2 outperforms VISinger, CpopSing andRefineSinger in both subjective and objective metrics.

VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer