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

Conversion of Chinese Grapheme-to-Phoneme (G2P) plays an important role inMandarin Chinese Text-To-Speech (TTS) systems, where one of the biggestchallenges is the task of polyphone disambiguation. Most of the previouspolyphone disambiguation models are trained on manually annotated datasets, andpublicly available datasets for polyphone disambiguation are scarce. In thispaper we propose a simple back-translation-style data augmentation method formandarin Chinese polyphone disambiguation, utilizing a large amount ofunlabeled text data. Inspired by the back-translation technique proposed in thefield of machine translation, we build a Grapheme-to-Phoneme (G2P) model topredict the pronunciation of polyphonic character, and a Phoneme-to-Grapheme(P2G) model to predict pronunciation into text. Meanwhile, a window-basedmatching strategy and a multi-model scoring strategy are proposed to judge thecorrectness of the pseudo-label. We design a data balance strategy to improvethe accuracy of some typical polyphonic characters in the training set withimbalanced distribution or data scarcity. The experimental result shows theeffectiveness of the proposed back-translation-style data augmentation method.

Back-Translation-Style Data Augmentation for Mandarin Chinese Polyphone Disambiguation