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

Expressive text-to-speech (TTS) has become a hot research topic recently,mainly focusing on modeling prosody in speech. Prosody modeling has severalchallenges: 1) the extracted pitch used in previous prosody modeling works haveinevitable errors, which hurts the prosody modeling; 2) different attributes ofprosody (e.g., pitch, duration and energy) are dependent on each other andproduce the natural prosody together; and 3) due to high variability of prosodyand the limited amount of high-quality data for TTS training, the distributionof prosody cannot be fully shaped. To tackle these issues, we proposeProsoSpeech, which enhances the prosody using quantized latent vectorspre-trained on large-scale unpaired and low-quality text and speech data.Specifically, we first introduce a word-level prosody encoder, which quantizesthe low-frequency band of the speech and compresses prosody attributes in thelatent prosody vector (LPV). Then we introduce an LPV predictor, which predictsLPV given word sequence. We pre-train the LPV predictor on large-scale text andlow-quality speech data and fine-tune it on the high-quality TTS dataset.Finally, our model can generate expressive speech conditioned on the predictedLPV. Experimental results show that ProsoSpeech can generate speech with richerprosody compared with baseline methods.

ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech