Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus on addressing audio information only.In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual deep CNN (AVDCNN) SE model, which incorporates audio and visual streams into a unified network model.In the proposed AVDCNN SE model,audio and visual features are first processed using individual CNNs, and then, fused into a joint network to generate enhanced speech at an output layer. The AVDCNN model is trained in an end-to-end manner, and parameters are jointly learned through back-propagation. We evaluate enhanced speech using five objective criteria. Results show that the AVDCNN yields notably better performance as compared to an audio-only CNN-based SE model, confirming the effectiveness of integrating visual information into the SE process.
View on arXiv