Untangling in Invariant Speech Recognition

by   Cory Stephenson, et al.

Encouraged by the success of deep neural networks on a variety of visual tasks, much theoretical and experimental work has been aimed at understanding and interpreting how vision networks operate. Meanwhile, deep neural networks have also achieved impressive performance in audio processing applications, both as sub-components of larger systems and as complete end-to-end systems by themselves. Despite their empirical successes, comparatively little is understood about how these audio models accomplish these tasks. In this work, we employ a recently developed statistical mechanical theory that connects geometric properties of network representations and the separability of classes to probe how information is untangled within neural networks trained to recognize speech. We observe that speaker-specific nuisance variations are discarded by the network's hierarchy, whereas task-relevant properties such as words and phonemes are untangled in later layers. Higher level concepts such as parts-of-speech and context dependence also emerge in the later layers of the network. Finally, we find that the deep representations carry out significant temporal untangling by efficiently extracting task-relevant features at each time step of the computation. Taken together, these findings shed light on how deep auditory models process time dependent input signals to achieve invariant speech recognition, and show how different concepts emerge through the layers of the network.


page 1

page 2

page 3

page 4


Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems

Neural models have become ubiquitous in automatic speech recognition sys...

NIESR: Nuisance Invariant End-to-end Speech Recognition

Deep neural network models for speech recognition have achieved great su...

Sequence Training and Adaptation of Highway Deep Neural Networks

Highway deep neural network (HDNN) is a type of depth-gated feedforward ...

Intriguing properties of neural networks

Deep neural networks are highly expressive models that have recently ach...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset