J
Jasha Droppo
Researcher at Amazon.com
Publications - 127
Citations - 7084
Jasha Droppo is an academic researcher from Amazon.com. The author has contributed to research in topics: Word error rate & Acoustic model. The author has an hindex of 39, co-authored 119 publications receiving 6324 citations. Previous affiliations of Jasha Droppo include University of Washington & Microsoft.
Papers
More filters
Proceedings ArticleDOI
1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs.
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.
Posted Content
Achieving Human Parity in Conversational Speech Recognition
Wayne Xiong,Jasha Droppo,Xuedong Huang,Frank Seide,Michael L. Seltzer,Andreas Stolcke,Dong Yu,Geoffrey Zweig +7 more
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.
An Introduction to Computational Networks and the Computational Network Toolkit
Dong Yu,Adam Eversole,Michael L. Seltzer,Kaisheng Yao,Oleksii Kuchaiev,Yu Zhang,Frank Seide,Zhiheng Huang,Brian Guenter,Huaming Wang,Jasha Droppo,Geoffrey Zweig,Christopher J. Rossbach,Jie Gao,Andreas Stolcke,Jon Currey,Malcolm Slaney,Guoguo Chen,Amit Kumar Agarwal,Christopher H. Basoglu,Marko Padmilac,Alexey Kamenev,Vladimir Ivanov,Scott Cypher,Hari Parthasarathi,Bhaskar Mitra,Baolin Peng,Xuedong Huang +27 more
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.
Proceedings ArticleDOI
The Microsoft 2017 Conversational Speech Recognition System
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.
Proceedings ArticleDOI
The microsoft 2016 conversational speech recognition system
Wayne Xiong,Jasha Droppo,Xuedong Huang,Frank Seide,Michael L. Seltzer,Andreas Stolcke,Dong Yu,Geoffrey Zweig +7 more
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.