The Microsoft 2016 Conversational Speech Recognition System

09/12/2016
by   W. Xiong, et al.
0

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 system uses a ResNet architecture acoustic model with RNNLM rescoring, and achieves a word error rate of 6.9 combined system has an error rate of 6.2 previously reported results on this benchmark task.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset