1. Understanding the difficulty of training deep feedforward neural networks;glorot;Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics JMLR Workshop and Conference Proceedings,2010
2. Joint Unsupervised and Supervised Training for Multilingual ASR
3. Adam: A method for stochastic optimization;kingma;International Conference on Learning Representations (ICLR),2015
4. Conformer: Convolution-augmented Transformer for Speech Recognition
5. Self-supervised learning with random-projection quantizer for speech recognition;chiu;International Conference on Machine Learning,2022