Context-dependent modelling of deep neural network using logistic regression

4 citations recorded by the source corpus.

How researchers see this paper

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

Deep Learning: Methods and Applications (2014, background): “In [383, 384], a limitation of the output representation design, based on the context-dependent phone units as proposed in [67, 68], is recognized and a solution is offered.”
Regression-Based Context-Dependent Modeling of Deep Neural Networks for Speech Recognition (2014, methodology): “To address this data sparsity problem, regression parameter tying is performed to reduce the model complexity by using decision tree state clusters (senones) as regression targets, where all CD states within the same cluster share the same set of regression weights.”