1. Jasper: an end-to-end convolutional neural acoustic model;Li;arXiv Preprint,2019
2. Recurrent Neural Networks for Noise Reduction in Robust ASR;Maas,2012
3. Robust audio-visual speech recognition under noisy audio-video conditions;Stewart;IEEE Trans. Cybernet.,2013
4. Vision-infused deep audio inpainting;Zhou,2019
5. Reconstructing Intelligible Audio Speech from Visual Speech Features;Milner,2015