Phone recognition using Restricted Boltzmann Machines

By Abdel-rahman Mohamed, Geoffrey E. Hinton. 2010

117 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Deep learning in neural networks: An overview (2014, neutral): “…result helped to arouse interest in DBNs. DBNs also achieved good results on phoneme recognition, with an error rate of 26.7% on the TIMIT core test set (Mohamed & Hinton, 2010); compare further improvements through FNNs (Deng & Yu, 2014; Hinton, Deng, et al., 2012) and LSTM RNNs (Section 5.22).”
Rectified Linear Units Improve Restricted Boltzmann Machines (2010, background): “…many diﬀerent types of data including labeled or unlabeled images (Hinton et al., 2006), sequences of mel-cepstral coef-ﬁcients that represent speech (Mohamed & Hinton, 2010), bags of words that represent documents (Salakhutdinov & Hinton, 2009), and user ratings of movies (Salakhutdinov et al.,…”
TIMIT Acoustic-Phonetic Continuous Speech Corpus (2012, methodology): “A new automatic learning technique for speech recognition applications has recently been presented (Mohamed & Hinton, 2010).”
Phone Recognition on the TIMIT Database (2012, methodology): “A new automatic learning technique for speech recognition applications has recently been presented (Mohamed & Hinton, 2010).”
Training restricted Boltzmann machines: An introduction (2014, background): “1 Introduction In the last years, models extending or borrowing concepts from restricted Boltzmann machines (RBMs, [49]) have enjoyed much popularity for pattern analysis and generation, with applications including image classification, processing, and generation [25, 51, 34, 28, 48, 31]; learning m”
Investigation of full-sequence training of deep belief networks for speech recognition (2010, background): “This strategy has proved to be effective in a number of applications including coding and classification for speech, audio, and image [6][8][9][12][13][14].”
Factorial Hidden Restricted Boltzmann Machines for noise robust speech recognition (2012, unknown): “Restricted Boltzmann machines (RBMs) have recently been applied to several well established problems in machine learning and signal processing, with great success.”
A Practical Guide to Training Restricted Boltzmann Machines (2012, background): “In their conditional form they can be used to model high-dimensional temporal sequences such as video or motion capture data (Taylor et al., 2006) or speech (Mohamed and Hinton, 2010).”
Sparse Multilayer Perceptron for Phoneme Recognition (2012, methodology): “Recently, restricted Boltzmann machine (RBM) is also used for estimating the posterior probabilities for phoneme recognition [27], [28].”
A review of unsupervised feature learning and deep learning for time-series modeling (2014, background): “However, the main problem with HMMs are that they require a discrete state space, often have unrealistic independence assumptions, and have a limited representational capacity of their hidden states (Mohamed and Hinton, 2010).”
Conditional restricted Boltzmann machine for voice conversion (2013, methodology): “Motivated by the success of restricted Boltzmann machine and conditional restricted Boltzmann machine in speech recognition [11], we proposed to utilize conditional restricted Boltzmann machine to estimate a robust conversion function for voice conversion.”