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

Self-Supervised Learning (SSL) Automatic Speech Recognition (ASR) models haveshown great promise over Supervised Learning (SL) ones in low-resourcesettings. However, the advantages of SSL are gradually weakened when the amountof labeled data increases in many industrial applications. To further improvethe ASR performance when abundant labels are available, we first explore thepotential of combining SL and SSL ASR models via analyzing theircomplementarity in recognition accuracy and optimization property. Then, wepropose a novel Optimal Transport based Fusion (OTF) method for SL and SSLmodels without incurring extra computation cost in inference. Specifically,optimal transport is adopted to softly align the layer-wise weights to unifythe two different networks into a single one. Experimental results on thepublic 1k-hour English LibriSpeech dataset and our in-house 2.6k-hour Chinesedataset show that OTF largely outperforms the individual models with lowererror rates.

OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition