Sequence Training and Adaptation of Highway Deep Neural Networks

TL;DR

This paper explores the use of highway deep neural networks with tied gate functions for speech recognition, demonstrating improved accuracy through sequence training and speaker adaptation by updating gate functions alone.

Contribution

It introduces a sequence training and speaker adaptation approach for highway deep neural networks with tied gate functions, showing these gates effectively control information flow and enhance recognition performance.

Findings

Sequence-discriminative training improves accuracy.

Speaker adaptation benefits from updating gate functions.

Tied gate functions effectively control information flow.

Abstract

Highway deep neural network (HDNN) is a type of depth-gated feedforward neural network, which has shown to be easier to train with more hidden layers and also generalise better compared to conventional plain deep neural networks (DNNs). Previously, we investigated a structured HDNN architecture for speech recognition, in which the two gate functions were tied across all the hidden layers, and we were able to train a much smaller model without sacrificing the recognition accuracy. In this paper, we carry on the study of this architecture with sequence-discriminative training criterion and speaker adaptation techniques on the AMI meeting speech recognition corpus. We show that these two techniques improve speech recognition accuracy on top of the model trained with the cross entropy criterion. Furthermore, we demonstrate that the two gate functions that are tied across all the hidden layers are able to control the information flow over the whole network, and we can achieve considerable improvements by only updating these gate functions in both sequence training and adaptation experiments.