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

Deep learning-based pronunciation scoring models highly rely on theavailability of the annotated non-native data, which is costly and hasscalability issues. To deal with the data scarcity problem, data augmentationis commonly used for model pretraining. In this paper, we propose a phone-levelmixup, a simple yet effective data augmentation method, to improve theperformance of word-level pronunciation scoring. Specifically, given a phonemesequence from lexicon, the artificial augmented word sample can be generated byrandomly sampling from the corresponding phone-level features in training data,while the word score is the average of their GOP scores. Benefit from thearbitrary phone-level combination, the mixup is able to generate any word withvarious pronunciation scores. Moreover, we utilize multi-source information(e.g., MFCC and deep features) to further improve the scoring systemperformance. The experiments conducted on the Speechocean762 show that theproposed system outperforms the baseline by adding the mixup data forpretraining, with Pearson correlation coefficients (PCC) increasing from 0.567to 0.61. The results also indicate that proposed method achieves similarperformance by using 1/10 unlabeled data of baseline. In addition, theexperimental results also demonstrate the efficiency of our proposedmulti-source approach.

Improving Non-native Word-level Pronunciation Scoring with Phone-level Mixup Data Augmentation and Multi-source Information