Search Results for author: J. Droppo

Found 4 papers, 0 papers with code

The Microsoft 2017 Conversational Speech Recognition System

no code implementations21 Aug 2017 W. Xiong, L. Wu, F. Alleva, J. Droppo, X. Huang, A. Stolcke

We describe the 2017 version of Microsoft's conversational speech recognition system, in which we update our 2016 system with recent developments in neural-network-based acoustic and language modeling to further advance the state of the art on the Switchboard speech recognition task.

Language Modelling speech-recognition +1

Achieving Human Parity in Conversational Speech Recognition

no code implementations17 Oct 2016 W. Xiong, J. Droppo, X. Huang, F. Seide, M. Seltzer, A. Stolcke, D. Yu, G. Zweig

Conversational speech recognition has served as a flagship speech recognition task since the release of the Switchboard corpus in the 1990s.

Language Modelling speech-recognition +1

Advances in All-Neural Speech Recognition

no code implementations19 Sep 2016 G. Zweig, C. Yu, J. Droppo, A. Stolcke

This paper advances the design of CTC-based all-neural (or end-to-end) speech recognizers.

Language Modelling speech-recognition +1

The Microsoft 2016 Conversational Speech Recognition System

no code implementations12 Sep 2016 W. Xiong, J. Droppo, X. Huang, F. Seide, M. Seltzer, A. Stolcke, D. Yu, G. Zweig

We describe Microsoft's conversational speech recognition system, in which we combine recent developments in neural-network-based acoustic and language modeling to advance the state of the art on the Switchboard recognition task.

Language Modelling speech-recognition +1

Cannot find the paper you are looking for? You can Submit a new open access paper.