论文信息 - Techniques for Improving Training Time of Deep Neural Networks with Applications to Speech Recognition - 字舞流文

Techniques for Improving Training Time of Deep Neural Networks with Applications to Speech Recognition

Tara N. Sainath | T. Sainath

[1] George Saon,et al. A comparison of two optimization techniques for sequence discriminative training of deep neural networks , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2] Tara N. Sainath,et al. Accelerating Hessian-free optimization for Deep Neural Networks by implicit preconditioning and sampling , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[3] Dong Yu,et al. Error back propagation for sequence training of Context-Dependent Deep NetworkS for conversational speech transcription , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[4] Yifan Gong,et al. Restructuring of deep neural network acoustic models with singular value decomposition , 2013, INTERSPEECH.

[5] Daniel Povey,et al. Krylov Subspace Descent for Deep Learning , 2011, AISTATS.

[6] Tara N. Sainath,et al. Scalable Minimum Bayes Risk Training of Deep Neural Network Acoustic Models Using Distributed Hessian-free Optimization , 2012, INTERSPEECH.

[7] James Martens,et al. Deep learning via Hessian-free optimization , 2010, ICML.