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

Singing voice synthesis has been paid rising attention with the rapiddevelopment of speech synthesis area. In general, a studio-level singing corpusis usually necessary to produce a natural singing voice from lyrics andmusic-related transcription. However, such a corpus is difficult to collectsince it's hard for many of us to sing like a professional singer. In thispaper, we propose an approach -- Learn2Sing that only needs a singing teacherto generate the target speakers' singing voice without their singing voicedata. In our approach, a teacher's singing corpus and speech from multipletarget speakers are trained in a frame-level auto-regressive acoustic modelwhere singing and speaking share the common speaker embedding and style tagembedding. Meanwhile, since there is no music-related transcription for thetarget speaker, we use log-scale fundamental frequency (LF0) as an auxiliaryfeature as the inputs of the acoustic model for building a unified inputrepresentation. In order to enable the target speaker to sing without singingreference audio in the inference stage, a duration model and an LF0 predictionmodel are also trained. Particularly, we employ domain adversarial training(DAT) in the acoustic model, which aims to enhance the singing performance oftarget speakers by disentangling style from acoustic features of singing andspeaking data. Our experiments indicate that the proposed approach is capableof synthesizing singing voice for target speaker given only their speechsamples.

Learn2Sing: Target Speaker Singing Voice Synthesis by learning from a Singing Teacher