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

We present a new approach to disentangle speaker voice and phone content byintroducing new components to the VQ-VAE architecture for speech synthesis. Theoriginal VQ-VAE does not generalize well to unseen speakers or content. Toalleviate this problem, we have incorporated a speaker encoder and speaker VQcodebook that learns global speaker characteristics entirely separate from theexisting sub-phone codebooks. We also compare two training methods:self-supervised with global conditions and semi-supervised with speaker labels.Adding a speaker VQ component improves objective measures of speech synthesisquality (estimated MOS, speaker similarity, ASR-based intelligibility) andprovides learned representations that are meaningful. Our speaker VQ codebookindices can be used in a simple speaker diarization task and perform slightlybetter than an x-vector baseline. Additionally, phones can be recognized fromsub-phone VQ codebook indices in our semi-supervised VQ-VAE better thanself-supervised with global conditions.

Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm