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 paper proposes a novel, resource-efficient approach to Visual SpeechRecognition (VSR) leveraging speech representations produced by any trainedAutomatic Speech Recognition (ASR) model. Moving away from theresource-intensive trends prevalent in recent literature, our method distillsknowledge from a trained Conformer-based ASR model, achieving competitiveperformance on standard VSR benchmarks with significantly less resourceutilization. Using unlabeled audio-visual data only, our baseline modelachieves a word error rate (WER) of 47.4% and 54.7% on the LRS2 and LRS3 testbenchmarks, respectively. After fine-tuning the model with limited labeleddata, the word error rate reduces to 35% (LRS2) and 45.7% (LRS3). Our model canbe trained on a single consumer-grade GPU within a few days and is capable ofperforming real-time end-to-end VSR on dated hardware, suggesting a pathtowards more accessible and resource-efficient VSR methodologies.

LiteVSR: Efficient Visual Speech Recognition by Learning from Speech Representations of Unlabeled Data