Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition

07/30/2018
by   Pavel Denisov, et al.
4

In this paper, we investigate the use of adversarial learning for unsupervised adaptation to unseen recording conditions, more specifically, single microphone far-field speech. We adapt neural networks based acoustic models trained with close-talk clean speech to the new recording conditions using untranscribed adaptation data. Our experimental results on Italian SPEECON data set show that our proposed method achieves 19.8 error rate (WER) reduction compared to the unadapted models. Furthermore, this adaptation method is beneficial even when performed on data from another language (i.e. French) giving 12.6

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/24/2019

Unsupervised Adversarial Domain Adaptation Based On The Wasserstein Distance For Acoustic Scene Classification

A challenging problem in deep learning-based machine listening field is ...
research
08/04/2021

Unsupervised Domain Adaptation in Speech Recognition using Phonetic Features

Automatic speech recognition is a difficult problem in pattern recogniti...
research
12/19/2021

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

We investigate densely connected convolutional networks (DenseNets) and ...
research
08/31/2017

Leveraging Deep Neural Network Activation Entropy to cope with Unseen Data in Speech Recognition

Unseen data conditions can inflict serious performance degradation on sy...
research
04/02/2018

Adversarial Teacher-Student Learning for Unsupervised Domain Adaptation

The teacher-student (T/S) learning has been shown effective in unsupervi...
research
09/06/2020

Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptation

This paper introduces a new dataset, Libri-Adapt, to support unsupervise...
research
04/04/2022

Robust Stuttering Detection via Multi-task and Adversarial Learning

By automatic detection and identification of stuttering, speech patholog...

Please sign up or login with your details

Forgot password? Click here to reset