Jan Chorowski: Deep neural networks for speech and natural language processing

Deep neural networks yield state of the art performance in speech recognition and allow for endtoend training in which of a model s components collaborate to solve the task at hand. I will present endtoend trainable attentionbased recurrent neural networks that directly directly transcribe speech features into sequences of phonemes or characters. The networks learn the alignment between the speech and its transcription and are trained directly to optimize the probability of the correct transcription. I