arXiv:1609.03528cs.CL
The Microsoft 2016 Conversational Speech Recognition System
Abstract
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.
It measures against what humans write down when they listen. Humans generally use context, so I'd expect that they would record "cloud" if that was appropriate in context. The Microsoft system also does this: it uses language modelling to attempt to model what word is more…
nlView on HNParent context
https://github.com/kaldi-asr/kaldi/blob/master/egs/fisher_sw... In Microsoft paper http://arxiv.org/pdf/1609.03528v1.pdf Table 5 it's a line "Povey et al. [19] LSTM". http://www.isca-speech.org/archive/Interspeech_2016/pdfs/059... Interpolate it to RNNLM column and you'll get…
nshmView on HNParent context
The paper itself can be found here https://arxiv.org/pdf/1609.03528v1.pdf quite interesting to see that the failure rate is lower than the average human failure rate, can't wait to see how this will improve over the coming years.
rngesusView on HNParent context
From the linked arxiv paper, http://arxiv.org/abs/1609.03528 this is a very interesting use of CNTK to adapt image CNN techniques to speech recognition. Surprising that CNNs worked so well on speech audio. Full disclosure: I am a MSFT employee.
cbasogluView on HNParent context