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

Most existing neural-based text-to-speech methods rely on extensive datasetsand face challenges under low-resource condition. In this paper, we introduce anovel semi-supervised text-to-speech synthesis model that learns from bothpaired and unpaired data to address this challenge. The key component of theproposed model is a dynamic quantized representation module, which isintegrated into a sequential autoencoder. When given paired data, the moduleincorporates a trainable codebook that learns quantized representations underthe supervision of the paired data. However, due to the limited paired data inlow-resource scenario, these paired data are difficult to cover all phonemes.Then unpaired data is fed to expand the dynamic codebook by adding quantizedrepresentation vectors that are sufficiently distant from the existing onesduring training. Experiments show that with less than 120 minutes of paireddata, the proposed method outperforms existing methods in both subjective andobjective metrics.

DQR-TTS: Semi-supervised Text-to-speech Synthesis with Dynamic Quantized Representation