Jasha Droppo

TL;DR: This work shows empirically that in SGD training of deep neural networks, one can, at no or nearly no loss of accuracy, quantize the gradients aggressively—to but one bit per value—if the quantization error is carried forward across minibatches (error feedback), and implements data-parallel deterministically distributed SGD by combining this finding with AdaGrad.

TL;DR: The human error rate on the widely used NIST 2000 test set is measured, and the latest automated speech recognition system has reached human parity, establishing a new state of the art, and edges past the human benchmark.

TL;DR: The computational network toolkit (CNTK), an implementation of CN that supports both GPU and CPU, is introduced and the architecture and the key components of the CNTK are described, the command line options to use C NTK, and the network definition and model editing language are described.

TL;DR: The latest version of Microsoft's conversational speech recognition system for the Switchboard and CallHome domains is described, which adds a CNN-BLSTM acoustic model to the set of model architectures combined previously, and includes character-based and dialog session aware LSTM language models in rescoring.

TL;DR: Microsoft's conversational speech recognition system is described, in which recent developments in neural-network-based acoustic and language modeling are combined to advance the state of the art on the Switchboard recognition task.