Weekly reading

报告

• 刘超2015-03-11 Towards End-to-End Speech Recognition with Recurrent Neural Networks

• 汤志远2015-3-18 - Building DNN Acoustic Models for Large Vocabulary Speech Recognition

• 林一叶2015-4-1 - CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION

• 张雪薇2015-4-1 - speech dereverberation using weighted prediction error with laplacian model of the designed signal

• 王东2015-4-1 - Do Deep Nets Really Need to be Deep?

• 王东2015-4-1 - Distilling the Knowledge in a Neural Network

• 殷实2015-4-8 - Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition

• 赵梦原2015-4-8 - Ensemble_Deep_Learning_for_Speech_Recognition

• 曾翔宇2015-3-11 - An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment

• 刘超2015-04-14 Real-time one-pass decoding with recurrent neural network language model for speech recognition

• 汤志远 2015-04-29 Reshaping deep neural network for fast decoding by node-pruning

• 张雪薇2015-4-29 SPEECH DEREVERBERATION WITH MULTI-CHANNEL LINEAR PREDICTION AND SPARSE PRIORS FOR THE DESIRED SIGNAL

• 张雪薇2015-4-29 MULTI-CHANNEL LINEAR PREDICTION-BASED SPEECH DEREVERBERATION WITH LOW-RANK POWER SPECTROGRAM APPROXIMATION

• 张之勇2015-5-6 On the importance of initialization and momentum in deep learning.pdf