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 study describes our system for Task 1 Single-speaker Visual SpeechRecognition (VSR) fixed track in the Chinese Continuous Visual SpeechRecognition Challenge (CNVSRC) 2023. Specifically, we use intermediateconnectionist temporal classification (Inter CTC) residual modules to relax theconditional independence assumption of CTC in our model. Then we use abi-transformer decoder to enable the model to capture both past and futurecontextual information. In addition, we use Chinese characters as the modelingunits to improve the recognition accuracy of our model. Finally, we use arecurrent neural network language model (RNNLM) for shallow fusion in theinference stage. Experiments show that our system achieves a character errorrate (CER) of 38.09% on the Eval set which reaches a relative CER reduction of21.63% over the official baseline, and obtains a second place in the challenge.

The GUA-Speech System Description for CNVSRC Challenge 2023