Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognition

12/19/2021
by   Chia Yu Li, et al.
0

We investigate densely connected convolutional networks (DenseNets) and their extension with domain adversarial training for noise robust speech recognition. DenseNets are very deep, compact convolutional neural networks which have demonstrated incredible improvements over the state-of-the-art results in computer vision. Our experimental results reveal that DenseNets are more robust against noise than other neural network based models such as deep feed forward neural networks and convolutional neural networks. Moreover, domain adversarial learning can further improve the robustness of DenseNets against both, known and unknown noise conditions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/10/2018

Densely Connected Convolutional Networks for Speech Recognition

This paper presents our latest investigation on Densely Connected Convol...
research
07/30/2018

Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition

In this paper, we investigate the use of adversarial learning for unsupe...
research
02/03/2020

Adversarial-based neural networks for affect estimations in the wild

There is a growing interest in affective computing research nowadays giv...
research
03/10/2018

Speech Recognition: Keyword Spotting Through Image Recognition

The problem of identifying voice commands has always been a challenge du...
research
02/03/2020

Adversarial-based neural network for affect estimations in the wild

There is a growing interest in affective computing research nowadays giv...
research
07/10/2023

SparseVSR: Lightweight and Noise Robust Visual Speech Recognition

Recent advances in deep neural networks have achieved unprecedented succ...
research
09/29/2020

Lip-reading with Densely Connected Temporal Convolutional Networks

In this work, we present the Densely Connected Temporal Convolutional Ne...

Please sign up or login with your details

Forgot password? Click here to reset