Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training

11/26/2020
by   Sameer Khurana, et al.
0

The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched. In this paper, we show that self-training (ST) combined with an uncertainty-based pseudo-label filtering approach can be effectively used for domain adaptation. We propose DUST, a dropout-based uncertainty-driven self-training technique which uses agreement between multiple predictions of an ASR system obtained for different dropout settings to measure the model's uncertainty about its prediction. DUST excludes pseudo-labeled data with high uncertainties from the training, which leads to substantially improved ASR results compared to ST without filtering, and accelerates the training time due to a reduced training data set. Domain adaptation experiments using WSJ as a source domain and TED-LIUM 3 as well as SWITCHBOARD as the target domains show that up to 80 be recovered.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/14/2022

On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration

Pseudo-label (PL) filtering forms a crucial part of Self-Training (ST) m...
research
09/14/2020

Unsupervised Domain Adaptation by Uncertain Feature Alignment

Unsupervised domain adaptation (UDA) deals with the adaptation of models...
research
04/15/2021

Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching

End-to-end automatic speech recognition (ASR) can achieve promising perf...
research
03/27/2022

Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition

Although deep learning-based end-to-end Automatic Speech Recognition (AS...
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
12/31/2022

Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greek

Modern speech recognition systems exhibits rapid performance degradation...
research
04/12/2019

Unsupervised Speech Domain Adaptation Based on Disentangled Representation Learning for Robust Speech Recognition

In general, the performance of automatic speech recognition (ASR) system...

Please sign up or login with your details

Forgot password? Click here to reset