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

Recently, sequence-to-sequence (seq-to-seq) models have been successfullyapplied in text-to-speech (TTS) to synthesize speech for single-language text.To synthesize speech for multiple languages usually requires multi-lingualspeech from the target speaker. However, it is both laborious and expensive tocollect high-quality multi-lingual TTS data for the target speakers. In thispaper, we proposed to use low-quality code-switched found data from thenon-target speakers to achieve cross-lingual voice cloning for the targetspeakers. Experiments show that our proposed method can generate high-qualitycode-switched speech in the target voices in terms of both naturalness andspeaker consistency. More importantly, we find that our method can achieve acomparable result to the state-of-the-art (SOTA) performance in cross-lingualvoice cloning.

Improve Cross-lingual Voice Cloning Using Low-quality Code-switched Data