Without proper planning, the scaling process can feel like patching a leaky pipe—constantly reacting to problems instead of ...

Although neural network-based speech recognition models have enjoyed significant success in many acoustic systems, they are susceptible to be attacked by the adversarial examples. In this work, we ...

Long short-term memory networks (LSTM) and gate recurrent unit networks (GRU) are two popular variants of recurrent neural networks (RNN) with long-term memory. Th ...