Canonical cortical graph neural networks and its application for speech enhancement in audio-visual hearing aids

Passos, Leandro A.; Papa, João Paulo; Hussain, Amir; Adeel, Ahsan

Abstract

Despite the recent success of machine learning algorithms, most models face drawbacks when considering more complex tasks requiring interaction between different sources, such as multimodal input data and logical time sequences. On the other hand, the biological brain is highly sharpened in this sense, empowered to automatically manage and integrate such streams of information. In this context, this work draws inspiration from recent discoveries in brain cortical circuits to propose a more biologically plausible self-supervised machine learning approach. This combines multimodal information using intra-layer modulations together with Canonical Correlation Analysis, and a memory mechanism to keep track of temporal data, the overall approach termed Canonical Cortical Graph Neural networks. This is shown to outperform recent state-of-the-art models in terms of clean audio reconstruction and energy efficiency for a benchmark audio-visual speech dataset. The enhanced performance is demonstrated through a reduced and smother neuron firing rate distribution. suggesting that the proposed model is amenable for speech enhancement in future audio-visual hearing aid devices.

Citation

Passos, L. A., Papa, J. P., Hussain, A., & Adeel, A. (2023). Canonical cortical graph neural networks and its application for speech enhancement in audio-visual hearing aids. Neurocomputing, 527, 196-203. https://doi.org/10.1016/j.neucom.2022.11.081

• Journal Article Type: Article
• Acceptance Date: Nov 21, 2022
• Online Publication Date: Dec 8, 2022
• Publication Date: 2023-03
• Deposit Date: Mar 2, 2023
• Publicly Available Date: Mar 2, 2023
• Journal: Neurocomputing
• Print ISSN: 0925-2312
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 527
• Pages: 196-203
• DOI: https://doi.org/10.1016/j.neucom.2022.11.081
• Keywords: Cortical circuits, Canonical correlation analysis, Multimodal learning, Graph neural network, Prior frames neighborhood, Positional encoding