Acoustic Modeling Using Deep Belief Networks
作者： Abdel-rahman Mohamed , George E. Dahl , Geoffrey Hinton
DOI: 10.1109/TASL.2011.2109382
关键词:
摘要: … directed generative model called a “deep belief net” (DBN) that has … network that was initialized using a generatively trained deep belief net, even though the feedforward neural network …
acm.org
toronto.edu 
utoronto.ca 
sci-hub.se 参考文章(41)
Geoffrey E. Hinton, A Practical Guide to Training Restricted Boltzmann Machines Neural Networks: Tricks of the Trade (2nd ed.). pp. 599- 619 ,(2012) , 10.1007/978-3-642-35289-8_32
Geoffrey E. Hinton, Miguel Á. Carreira-Perpiñán, On Contrastive Divergence Learning. international conference on artificial intelligence and statistics. ,(2005)
Volodymyr Mnih, Geoffrey E. Hinton, Learning to Detect Roads in High-Resolution Aerial Images Computer Vision – ECCV 2010. pp. 210- 223 ,(2010) , 10.1007/978-3-642-15567-3_16
Yoshua Bengio, Artificial neural networks and their application to sequence recognition McGill University. ,(1991)
Volodymyr Mnih, CUDAMat: a CUDA-based matrix class for Python ,(2009)
Eric Fosler-Lussier, Jeremy Morris, Combining phonetic attributes using conditional random fields conference of the international speech communication association. ,(2006)
Hynek Hermansky, Sangita Sharma, TRAPS - classifiers of temporal patterns. conference of the international speech communication association. ,(1998)
Peter F. Brown, The acoustic-modeling problem in automatic speech recognition Interim Report Carnegie-Mellon Univ. ,(1987) , 10.21236/ADA188529
Herve A. Bourlard, Nelson Morgan, Connectionist Speech Recognition: A Hybrid Approach Kluwer Academic Publishers. ,(1993)
Andrew K. Halberstadt, James R. Glass, Heterogeneous measurements and multiple classifiers for speech recognition. conference of the international speech communication association. ,(1998)