tags notes author paper years SE_model MetricGAN Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement Szu-Wei Fu pdf 2019 ICML ASR A STREAMING ON-DEVICE END-TO-END MODEL SURPASSING SERVER-SIDE CONVENTIONAL MODEL QUALITY AND LATENCY Google pdf 2020.03 compress_SE Learning both Weights and Connections for Efficient Neural Networks Song Han, Jeff Pool, William J. Dally pdf 2015 train_method SpecAugment A Simple Data Augmentation Method for Automatic Speech Recognition Daniel S. Park∗, William Chan, Yu Zhang, Chung-Cheng Chiu pdf 2019 SE_model A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement Ke Tan, D. Wang pdf 2018 compress_SE Increasing Compactness Of Deep Learning Based Speech Enhancement Models With Parameter Pruning And Quantization Techniques Jyun-Yi Wu, Cheng Yu, Szu-Wei Fu pdf 2019 train_method on the difficulty of training rnn Razvan Pascanu, Tomas Mikolov, Yoshua Bengio pdf 2013 overview Supervised speech separation based on deep learning An overview D. Wang pdf 2018