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/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

This paper proposes a novel multimodal self-supervised architecture forenergy-efficient audio-visual (AV) speech enhancement that integrates GraphNeural Networks with canonical correlation analysis (CCA-GNN). The proposedapproach lays its foundations on a state-of-the-art CCA-GNN that learnsrepresentative embeddings by maximizing the correlation between pairs ofaugmented views of the same input while decorrelating disconnected features.The key idea of the conventional CCA-GNN involves discardingaugmentation-variant information and preserving augmentation-invariantinformation while preventing capturing of redundant information. Our proposedAV CCA-GNN model deals with multimodal representation learning context.Specifically, our model improves contextual AV speech processing by maximizingcanonical correlation from augmented views of the same channel and canonicalcorrelation from audio and visual embeddings. In addition, it proposes apositional node encoding that considers a prior-frame sequence distance insteadof a feature-space representation when computing the node's nearest neighbors,introducing temporal information in the embeddings through the neighborhood'sconnectivity. Experiments conducted on the benchmark ChiME3 dataset show thatour proposed prior frame-based AV CCA-GNN ensures better feature learning inthe temporal context, leading to more energy-efficient speech reconstructionthan state-of-the-art CCA-GNN and multilayer perceptron.

Multimodal Audio-Visual Information Fusion using Canonical-Correlated Graph Neural Network for Energy-Efficient Speech Enhancement