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

In recent years, deep learning based machine lipreading has gainedprominence. To this end, several architectures such as LipNet, LCANet andothers have been proposed which perform extremely well compared to traditionallipreading DNN-HMM hybrid systems trained on DCT features. In this work, wepropose a simpler architecture of 3D-2D-CNN-BLSTM network with a bottlenecklayer. We also present analysis of two different approaches for lipreading onthis architecture. In the first approach, 3D-2D-CNN-BLSTM network is trainedwith CTC loss on characters (ch-CTC). Then BLSTM-HMM model is trained onbottleneck lip features (extracted from 3D-2D-CNN-BLSTM ch-CTC network) in atraditional ASR training pipeline. In the second approach, same 3D-2D-CNN-BLSTMnetwork is trained with CTC loss on word labels (w-CTC). The first approachshows that bottleneck features perform better compared to DCT features. Usingthe second approach on Grid corpus' seen speaker test set, we report $1.3\%$WER - a $55\%$ improvement relative to LCANet. On unseen speaker test set wereport $8.6\%$ WER which is $24.5\%$ improvement relative to LipNet. We alsoverify the method on a second dataset of $81$ speakers which we collected.Finally, we also discuss the effect of feature duplication on BLSTM-HMM modelperformance.

LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models