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

In this paper, we propose VISinger, a complete end-to-end high-qualitysinging voice synthesis (SVS) system that directly generates audio waveformfrom lyrics and musical score. Our approach is inspired by VITS, which adoptsVAE-based posterior encoder augmented with normalizing flow-based prior encoderand adversarial decoder to realize complete end-to-end speech generation.VISinger follows the main architecture of VITS, but makes substantialimprovements to the prior encoder based on the characteristics of singing.First, instead of using phoneme-level mean and variance of acoustic features,we introduce a length regulator and a frame prior network to get theframe-level mean and variance on acoustic features, modeling the rich acousticvariation in singing. Second, we further introduce an F0 predictor to guide theframe prior network, leading to stabler singing performance. Finally, toimprove the singing rhythm, we modify the duration predictor to specificallypredict the phoneme to note duration ratio, helped with singing notenormalization. Experiments on a professional Mandarin singing corpus show thatVISinger significantly outperforms FastSpeech+Neural-Vocoder two-stage approachand the oracle VITS; ablation study demonstrates the effectiveness of differentcontributions.

VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis