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 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