Online Continual Learning of End-to-End Speech Recognition Models

07/11/2022
by   Muqiao Yang, et al.
0

Continual Learning, also known as Lifelong Learning, aims to continually learn from new data as it becomes available. While prior research on continual learning in automatic speech recognition has focused on the adaptation of models across multiple different speech recognition tasks, in this paper we propose an experimental setting for online continual learning for automatic speech recognition of a single task. Specifically focusing on the case where additional training data for the same task becomes available incrementally over time, we demonstrate the effectiveness of performing incremental model updates to end-to-end speech recognition models with an online Gradient Episodic Memory (GEM) method. Moreover, we show that with online continual learning and a selective sampling strategy, we can maintain an accuracy that is similar to retraining a model from scratch while requiring significantly lower computation costs. We have also verified our method with self-supervised learning (SSL) features.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/26/2021

Continual-wav2vec2: an Application of Continual Learning for Self-Supervised Automatic Speech Recognition

We present a method for continual learning of speech representations for...
research
12/02/2022

Continual Learning for On-Device Speech Recognition using Disentangled Conformers

Automatic speech recognition research focuses on training and evaluating...
research
06/12/2020

Move-to-Data: A new Continual Learning approach with Deep CNNs, Application for image-class recognition

In many real-life tasks of application of supervised learning approaches...
research
12/10/2018

Task-Free Continual Learning

Methods proposed in the literature towards continual deep learning typic...
research
05/12/2023

Continual Learning for End-to-End ASR by Averaging Domain Experts

Continual learning for end-to-end automatic speech recognition has to co...
research
02/23/2023

Evaluating Automatic Speech Recognition in an Incremental Setting

The increasing reliability of automatic speech recognition has prolifera...
research
02/25/2021

On continual single index learning

In this paper, we generalize the problem of single index model to the co...

Please sign up or login with your details

Forgot password? Click here to reset