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

This research optimizes two-pass cross-lingual transfer learning inlow-resource languages by enhancing phoneme recognition and phoneme-to-graphemetranslation models. Our approach optimizes these two stages to improve speechrecognition across languages. We optimize phoneme vocabulary coverage bymerging phonemes based on shared articulatory characteristics, thus improvingrecognition accuracy. Additionally, we introduce a global phoneme noisegenerator for realistic ASR noise during phoneme-to-grapheme training to reduceerror propagation. Experiments on the CommonVoice 12.0 dataset show significantreductions in Word Error Rate (WER) for low-resource languages, highlightingthe effectiveness of our approach. This research contributes to theadvancements of two-pass ASR systems in low-resource languages, offering thepotential for improved cross-lingual transfer learning.

Optimizing Two-Pass Cross-Lingual Transfer Learning: Phoneme Recognition and Phoneme to Grapheme Translation