Enhanced Phone Posteriors for Improving Speech Recognition Systems

By Hamed Ketabdar, Hervé Bourlard. 2010

41 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, background): “For some representative recent work in this area, see [193, 283].”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, background): “For some representative recent works in this area, see [104, 105].”
An Overview of Deep-Structured Learning for Information Processing (2011, background): “…of deep neural network models forms the basis of the popular ―tandem‖ approach, where a discriminatively learned neural network is developed in the context of computing discriminant emission probabilities for HMMs; for the most recent work, see (Pinto et al., 2011; Ketabdar and Bourlard, 2010).”
Convolutional deep maxout networks for phone recognition (2014, methodology): “This architecture was motivated by the success of hierarchical ANN models, where a neural network is trained on a block of acoustic feature vectors, and then a second network is trained on a block of posterior output vectors got from the first network [15, 16].”
Phone recognition with hierarchical convolutional deep maxout networks (2015, methodology): “Some authors observed that the posterior estimates obtained can be “enhanced” by training yet another network—but this time on a sequence of output vectors coming from the first network [22].”
Sparse Multilayer Perceptron for Phoneme Recognition (2012, background): “Further improvements are reported with the hierarchical estimation of the posterior probabilities [1]–[3].”