# Learning to adapt: a meta-learning approach for speaker adaptation

arXiv: https://arxiv.org/abs/1808.10239 · HTML: https://mlsanity.com/paper/1808.10239/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2018.

## Built on by (most cited first, 6 of 6)

- [Meta Learning for Natural Language Processing: A Survey](https://mlsanity.com/paper/2205.01500/) (2022)
- [Improved Meta Learning for Low Resource Speech Recognition](https://mlsanity.com/paper/2205.06182/) (2022)
- [In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties](https://mlsanity.com/paper/2505.14887/) (2025)
- [Writer adaptation for offline text recognition: An exploration of neural network-based methods](https://mlsanity.com/paper/2307.15071/) (2023)
- [Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading](https://mlsanity.com/paper/2310.05058/) (2023)
- [Towards Better Meta-Initialization with Task Augmentation for Kindergarten-aged Speech Recognition](https://mlsanity.com/paper/2202.12326/) (2022)

## Abstract (arXiv)

The performance of automatic speech recognition systems can be improved by adapting an acoustic model to compensate for the mismatch between training and testing conditions, for example by adapting to unseen speakers. The success of speaker adaptation methods relies on selecting weights that are suitable for adaptation and using good adaptation schedules to update these weights in order not to overfit to the adaptation data. In this paper we investigate a principled way of adapting all the weights of the acoustic model using a meta-learning. We show that the meta-learner can learn to perform supervised and unsupervised speaker adaptation and that it outperforms a strong baseline adapting LHUC parameters when adapting a DNN AM with 1.5M parameters. We also report initial experiments on adapting TDNN AMs, where the meta-learner achieves comparable performance with LHUC.