The microsoft 2016 conversational speech recognition system

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. Inspired by machine learning ensemble techniques, the system uses...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 5255 - 5259
Main Authors Xiong, W., Droppo, J., Huang, X., Seide, F., Seltzer, M., Stolcke, A., Yu, D., Zweig, G.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2017
Subjects
Acoustics
Adaptation models
BLSTM
Computational modeling
Conversational speech recognition
convolutional neural networks
Hidden Markov models
LACE
recurrent neural networks
ResNet
Speech recognition
Switches
Training
VGG
Online AccessGet full text

Cover

More Information
Summary: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. Inspired by machine learning ensemble techniques, the system uses a range of convolutional and recurrent neural networks. I-vector modeling and lattice-free MMI training provide significant gains for all acoustic model architectures. Language model rescoring with multiple forward and backward running RNNLMs, and word posterior-based system combination provide a 20% boost. The best single system uses a ResNet architecture acoustic model with RNNLM rescoring, and achieves a word error rate of 6.9% on the NIST 2000 Switchboard task. The combined system has an error rate of 6.2%, representing an improvement over previously reported results on this benchmark task.
ISSN:2379-190X
DOI:10.1109/ICASSP.2017.7953159