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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The goal of this work is to train strong models for visual speech recognitionwithout requiring human annotated ground truth data. We achieve this bydistilling from an Automatic Speech Recognition (ASR) model that has beentrained on a large-scale audio-only corpus. We use a cross-modal distillationmethod that combines Connectionist Temporal Classification (CTC) with aframe-wise cross-entropy loss. Our contributions are fourfold: (i) we show thatground truth transcriptions are not necessary to train a lip reading system;(ii) we show how arbitrary amounts of unlabelled video data can be leveraged toimprove performance; (iii) we demonstrate that distillation significantlyspeeds up training; and, (iv) we obtain state-of-the-art results on thechallenging LRS2 and LRS3 datasets for training only on publicly availabledata.

ASR is all you need: cross-modal distillation for lip reading