On the Role of Nonlinear Transformations in Deep Neural Network Acoustic Models

38 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.

Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems (2017, methodology): “In contrast, feed-forward neural networks trained on phoneme recognition were shown to learn increasingly better representations at higher layers [13, 14]; such networks do not need to model the full speech recognition task, different from end-to-end models.”
Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition (2017, background): “This effect has been found in systems for speech processing [14, 15] as well as computer vision [16, 17].”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, background): “For instance, previous work evaluated neural network acoustic models on phone recognition using different acoustic features [243] or investigated how such models learn invariant representations [352] and encode linguistic features in different layers [251, 252].”