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

The virtual world is being established in which digital humans are createdindistinguishable from real humans. Producing their audio-related capabilitiesis crucial since voice conveys extensive personal characteristics. We aim tocreate a controllable audio-form virtual singer; however, supervised modelingand controlling all different factors of the singing voice, such as timbre,tempo, pitch, and lyrics, is extremely difficult since accurately labeling allsuch information needs enormous labor work. In this paper, we propose aframework that could digitize a person's voice by simply "listening" to theclean voice recordings of any content in a fully unsupervised manner andpredict singing voices even only using speaking recordings. A variationalauto-encoder (VAE) based framework is developed, which leverages a set ofpre-trained models to encode the audio as various hidden embeddingsrepresenting different factors of the singing voice, and further decodes theembeddings into raw audio. By manipulating the hidden embeddings for differentfactors, the resulting singing voices can be controlled, and new virtualsingers can also be further generated by interpolating between timbres.Evaluations of different types of experiments demonstrate the proposed method'seffectiveness. The proposed method is the critical technique for producing theAI choir, which empowered the human-AI symbiotic orchestra in Hong Kong in July2022.

Learn to Sing by Listening: Building Controllable Virtual Singer by Unsupervised Learning from Voice Recordings