Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning

05/22/2023
by   Ruan van der Merwe, et al.
0

We consider the problem of few-shot spoken word classification in a setting where a model is incrementally introduced to new word classes. This would occur in a user-defined keyword system where new words can be added as the system is used. In such a continual learning scenario, a model might start to misclassify earlier words as newer classes are added, i.e. catastrophic forgetting. To address this, we propose an extension to model-agnostic meta-learning (MAML): each inner learning loop, where a model "learns how to learn” new classes, ends with a single gradient update using stored templates from all the classes that the model has already seen (one template per class). We compare this method to OML (another extension of MAML) in few-shot isolated-word classification experiments on Google Commands and FACC. Our method consistently outperforms OML in experiments where the number of shots and the final number of classes are varied.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/09/2021

Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition

Most meta-learning approaches assume the existence of a very large set o...
research
04/30/2020

Bayesian Online Meta-Learning with Laplace Approximation

Neural networks are known to suffer from catastrophic forgetting when tr...
research
01/29/2022

Progressive Continual Learning for Spoken Keyword Spotting

Catastrophic forgetting is a thorny challenge when updating keyword spot...
research
07/15/2022

Continual Learning For On-Device Environmental Sound Classification

Continuously learning new classes without catastrophic forgetting is a c...
research
06/29/2021

Representation based meta-learning for few-shot spoken intent recognition

Spoken intent detection has become a popular approach to interface with ...
research
06/30/2021

How to Train Your MAML to Excel in Few-Shot Classification

Model-agnostic meta-learning (MAML) is arguably the most popular meta-le...
research
09/17/2020

Few-Shot Unsupervised Continual Learning through Meta-Examples

In real-world applications, data do not reflect the ones commonly used f...

Please sign up or login with your details

Forgot password? Click here to reset