Audio-Visual Speech Enhancement Using Multimodal Deep Convolutional Neural Networks

Mathematics

• Speech Enhancement 100%
• Vision 54%
• Neural Networks 49%
• Speech 12%
• Model 11%
• Multi-task Learning 8%
• Speech Signal 7%
• Back Propagation 7%
• Output 7%
• Encoder 6%
• Modality 5%
• Network Model 5%
• Learning 4%
• Evaluate 3%
• Performance 2%
• Framework 2%

Engineering & Materials Science

• Speech enhancement 65%
• Audiovisual 61%
• Deep neural networks 51%
• Convolutional neural networks 48%
• Multi-task learning 7%
• Backpropagation 5%