===Group1===Google
:Convolutional, long short-term memory, fully connected deep neural networks, ICASSP 2015.Google
:Context dependent phone models for LSTM RNN acoustic modellingConvolutional, long short-term memory, fully connected deep neural networks, ICASSP 2015.
: Context dependent phone models for LSTM RNN acoustic modelling, ICASSP 2015. ===Group2===
Google
:Listen, attend and spell: A neural network for large vocabulary conversational speech recognition, ICASSP 2015. === Group3 ===
===Group3===
JHU
:Audio augmentation for speech recognition, InterSpeech 2015.
===Group4===
Baidu
:Deep Speech 2 End-to-End Speech Recognition in English and Mandarin, JMLR 2016.