arXiv:1708.06073cs.CL
The Microsoft 2017 Conversational Speech Recognition System
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
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. The system adds a CNN-BLSTM acoustic model to the set of model architectures we combined previously, and includes character-based and dialog session aware LSTM language models in rescoring. For system combination we adopt a two-stage approach, whereby subsets of acoustic models are first combined at the senone/frame level, followed by a word-level voting via confusion networks. We also added a confusion network rescoring step after system combination. The resulting system yields a 5.1\% word error rate on the 2000 Switchboard evaluation set.
Who am I to argue with your experience? I can only offer the current literature on the topic [0]. (They report a 5.1% error) > These systems typically use deep convolutional neural network (CNN) architectures ... driving the word error rate on the benchmark Switchboard corpus…
WehrdoView on HNParent context