Details

Autor(en) / Beteiligte

• Xiong, W.
• Wu, L.
• Alleva, F.
• Droppo, J.
• Huang, X.
• Stolcke, A.

Titel

The Microsoft 2017 Conversational Speech Recognition System

Ist Teil von

• 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, p.5934-5938

Ort / Verlag

IEEE

Erscheinungsjahr

2018

Link zum Volltext

• IEEE_Xplore

Quelle

IEEE Xplore

Beschreibungen/Notizen

• We describe the latest version of Microsoft's conversational speech recognition system for the Switchboard and CallHome domains. 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 acoustic model posteriors are first combined at the senone/frame level, followed by a word-level voting via confusion networks. We also added another language model rescoring step following the confusion network combination. The resulting system yields a 5.1% word error rate on the NIST 2000 Switchboard test set, and 9.8% on the CallHome subset.