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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

UniSpeech has achieved superior performance in cross-lingual automatic speechrecognition (ASR) by explicitly aligning latent representations to phonemeunits using multi-task self-supervised learning. While the learnedrepresentations transfer well from high-resource to low-resource languages,predicting words directly from these phonetic representations in downstream ASRis challenging. In this paper, we propose TranUSR, a two-stage model comprisinga pre-trained UniData2vec and a phoneme-to-word Transcoder. Different fromUniSpeech, UniData2vec replaces the quantized discrete representations withcontinuous and contextual representations from a teacher model forphonetically-aware pre-training. Then, Transcoder learns to translate phonemesto words with the aid of extra texts, enabling direct word generation.Experiments on Common Voice show that UniData2vec reduces PER by 5.3% comparedto UniSpeech, while Transcoder yields a 14.4% WER reduction compared tographeme fine-tuning.

TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representation Learning for Cross-lingual Speech Recognition