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

arXiv: https://arxiv.org/abs/2305.13080 · HTML: https://mlsanity.com/paper/2305.13080/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 22 May 2023.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Meta-Learning Representations for Continual Learning](https://mlsanity.com/paper/1905.12588/) (2019)
- [Learning to Continually Learn](https://mlsanity.com/paper/2002.09571/) (2020)
- [learn2learn: A Library for Meta-Learning Research](https://mlsanity.com/paper/2008.12284/) (2020)
- [Deep Multimodal Semantic Embeddings for Speech and Images](https://mlsanity.com/paper/1511.03690/) (2015)
- [Reproducibility Report: La-MAML: Look-ahead Meta Learning for Continual Learning](https://mlsanity.com/paper/2102.05824/) (2021)
- [Learning Fast Adaptation on Cross-Accented Speech Recognition](https://mlsanity.com/paper/2003.01901/) (2020)
- [MetaAudio: A Few-Shot Audio Classification Benchmark](https://mlsanity.com/paper/2204.02121/) (2022)
- [Multimodal One-Shot Learning of Speech and Images](https://mlsanity.com/paper/1811.03875/) (2018)
- [Data Efficient Direct Speech-to-Text Translation with Modality Agnostic Meta-Learning](https://mlsanity.com/paper/1911.04283/) (2019)
- [Speaker Adaptive Training using Model Agnostic Meta-Learning](https://mlsanity.com/paper/1910.10605/) (2019)
- [Progressive Continual Learning for Spoken Keyword Spotting](https://mlsanity.com/paper/2201.12546/) (2022)
- [On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spotting](https://mlsanity.com/paper/2204.00352/) (2022)

## Built on by (most cited first, 2 of 2)

- [Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents](https://mlsanity.com/paper/2604.08369/) (2026)
- [Scaling few-shot spoken word classification with generative meta-continual learning](https://mlsanity.com/paper/2605.13075/) (2026)

## Abstract (arXiv)

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.