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 a model to perform style transfer of speech tosinging voice. Contrary to the previous signal processing-based methods, whichrequire high-quality singing templates or phoneme synchronization, we explore adata-driven approach for the problem of converting natural speech to singingvoice. We develop a novel neural network architecture, called SymNet, whichmodels the alignment of the input speech with the target melody whilepreserving the speaker identity and naturalness. The proposed SymNet model iscomprised of symmetrical stack of three types of layers - convolutional,transformer, and self-attention layers. The paper also explores novel dataaugmentation and generative loss annealing methods to facilitate the modeltraining. Experiments are performed on the  NUS and NHSS datasets which consist of parallel data of speech and singingvoice. In these experiments, we show that the proposed SymNet model improvesthe objective reconstruction quality significantly over the previouslypublished methods and baseline architectures. Further, a subjective listeningtest confirms the improved quality of the audio obtained using the proposedapproach (absolute improvement of 0.37 in mean opinion score measure over thebaseline system).

Leveraging Symmetrical Convolutional Transformer Networks for Speech to Singing Voice Style Transfer