Sciweavers

Share
ICASSP
2011
IEEE

Large vocabulary continuous speech recognition with context-dependent DBN-HMMS

8 years 9 months ago
Large vocabulary continuous speech recognition with context-dependent DBN-HMMS
The context-independent deep belief network (DBN) hidden Markov model (HMM) hybrid architecture has recently achieved promising results for phone recognition. In this work, we propose a context-dependent DBN-HMM system that dramatically outperforms strong Gaussian mixture model (GMM)-HMM baselines on a challenging, large vocabulary, spontaneous speech recognition dataset from the Bing mobile voice search task. Our system achieves absolute sentence accuracy improvements of 5.8% and 9.2% over GMM-HMMs trained using the minimum phone error rate (MPE) and maximum likelihood (ML) criteria, respectively, which translate to relative error reductions of 16.0% and 23.2%.
George E. Dahl, Dong Yu, Li Deng, Alex Acero
Added 21 Aug 2011
Updated 21 Aug 2011
Type Journal
Year 2011
Where ICASSP
Authors George E. Dahl, Dong Yu, Li Deng, Alex Acero
Comments (0)
books