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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this paper, we present a novel architecture to realize fine-grained stylecontrol on the transformer-based text-to-speech synthesis (TransformerTTS).Specifically, we model the speaking style by extracting a time sequence oflocal style tokens (LST) from the reference speech. The existing contentencoder in TransformerTTS is then replaced by our designed cross-attentionblocks for fusion and alignment between content and style. As the fusion isperformed along with the skip connection, our cross-attention block provides agood inductive bias to gradually infuse the phoneme representation with a givenstyle. Additionally, we prevent the style embedding from encoding linguisticcontent by randomly truncating LST during training and using wav2vec 2.0features. Experiments show that with fine-grained style control, our systemperforms better in terms of naturalness, intelligibility, and styletransferability. Our code and samples are publicly available.

Fine-grained style control in Transformer-based Text-to-speech Synthesis