Backpropagation training for multilayer conditional random field based phone recognition

By Rohit Prabhavalkar, Eric Fosler-Lussier. 2010

43 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Deep Learning: Methods and Applications (2014, positive): “Also, the benefit of using the full-sequence classification criteria was shown earlier on shallow neural networks in [194, 291].”
Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks (2017, background): “Recently, they have shown state-of-the-art results in segmentation [15, 16] when combined with deep neural networks [17, 18, 19].”
Deep-structured hidden conditional random fields for phonetic recognition (2010, methodology): “Prabhavalkar and FoslerLussier [2] developed the multilayer conditional random fields (MCRFs) with back-propagation training and applied it to phone recognition.”
Hidden-Unit Conditional Random Fields (2011, background): “Hidden-unit CRFs also bear some resemblance to approaches that train a deep network (often in an unsupervised manner), and train a linear CRF or Viterbi decoder on the output of the resulting network (Do and Artieres, 2010; Lee et al., 2010; Mohamed et al., 2009; Prabhavalkar and Fosler-Lussier, 201”
Effect of Non-linear Deep Architecture in Sequence Labeling (2013, methodology): “This model also appeared previously in the speech recognition literature in Prabhavalkar and Fosler-Lussier (2010).”
Fully Connected Deep Structured Networks (2015, background): “More recently [5, 27, 22, 6, 28, 25] incorporate non-linearities into unary potentials but generally assume exact inference to be tractable.”
Deep segmental neural networks for speech recognition (2013, methodology): “A similar deep model to ours has been proposed for the CRF model in [19, 20, 21, 22] with the difference of being frame-based rather than being segment-based.”
Investigation of full-sequence training of deep belief networks for speech recognition (2010, background): “Using neural networks to discriminate between sequences has indeed been proposed in the past (e.g., [4][10][11][16], but it was done in shallow architectures and not in an integrative manner.”
Language modeling with neural trans-dimensional random fields (2017, background): “It also appeared previously in the speech recognition literature [13].”
Deep Neural Networks for Acoustic Modeling in Speech Recognition (2012, methodology): “IEEE SIGNAL PROCESSING MAGAZINE [8] NOvEMbER 2012 using such sequence classification criteria with shallow neural networks has already been shown by [36]–[38].”