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

This paper introduces the T23 team's system submitted to the Singing VoiceConversion Challenge 2023. Following the recognition-synthesis framework, oursinging conversion model is based on VITS, incorporating four key modules: aprior encoder, a posterior encoder, a decoder, and a parallel bank oftransposed convolutions (PBTC) module. We particularly leverage Whisper, apowerful pre-trained ASR model, to extract bottleneck features (BNF) as theinput of the prior encoder. Before BNF extraction, we perform pitchperturbation to the source signal to remove speaker timbre, which effectivelyavoids the leakage of the source speaker timbre to the target. Moreover, thePBTC module extracts multi-scale F0 as the auxiliary input to the priorencoder, thereby capturing better pitch variations of singing. We design athree-stage training strategy to better adapt the base model to the targetspeaker with limited target speaker data. Official challenge results show thatour system has superior performance in naturalness, ranking 1st and 2ndrespectively in Task 1 and 2. Further ablation justifies the effectiveness ofour system design.

VITS-Based Singing Voice Conversion Leveraging Whisper and multi-scale F0 Modeling