# Improved Meta Learning for Low Resource Speech Recognition

arXiv: https://arxiv.org/abs/2205.06182 · HTML: https://mlsanity.com/paper/2205.06182/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 24 references that are in the map.
- First posted on arXiv 11 May 2022.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [Few-shot Video-to-Video Synthesis](https://mlsanity.com/paper/1910.12713/) (2019)
- [Meta-Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1808.08437/) (2018)
- [End-to-end Text-to-speech for Low-resource Languages by Cross-Lingual Transfer Learning](https://mlsanity.com/paper/1904.06508/) (2019)
- [Meta Learning for End-to-End Low-Resource Speech Recognition](https://mlsanity.com/paper/1910.12094/) (2019)
- [Learning Fast Adaptation on Cross-Accented Speech Recognition](https://mlsanity.com/paper/2003.01901/) (2020)
- [Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages](https://mlsanity.com/paper/1806.05059/) (2018)
- [A Simple Neural Attentive Meta-Learner](https://mlsanity.com/paper/1707.03141/) (2017)
- [Speaker Adaptive Training using Model Agnostic Meta-Learning](https://mlsanity.com/paper/1910.10605/) (2019)
- [Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs](https://mlsanity.com/paper/2004.02863/) (2020)
- [DEEPF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals](https://mlsanity.com/paper/2102.06306/) (2021)
- [Learning to adapt: a meta-learning approach for speaker adaptation](https://mlsanity.com/paper/1808.10239/) (2018)

## Built on by (most cited first, 7 of 7)

- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [A Novel Self-training Approach for Low-resource Speech Recognition](https://mlsanity.com/paper/2308.05269/) (2023)
- [SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition](https://mlsanity.com/paper/2409.10429/) (2024)
- [Meta-Learning in Audio and Speech Processing: An End to End Comprehensive Review](https://mlsanity.com/paper/2408.10330/) (2024)
- [PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognition](https://mlsanity.com/paper/2312.08571/) (2023)
- [Robust Cross-Etiology and Speaker-Independent Dysarthric Speech Recognition](https://mlsanity.com/paper/2501.14994/) (2025)
- [Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning](https://mlsanity.com/paper/2412.01408/) (2024)

## Abstract (arXiv)

We propose a new meta learning based framework for low resource speech recognition that improves the previous model agnostic meta learning (MAML) approach. The MAML is a simple yet powerful meta learning approach. However, the MAML presents some core deficiencies such as training instabilities and slower convergence speed. To address these issues, we adopt multi-step loss (MSL). The MSL aims to calculate losses at every step of the inner loop of MAML and then combines them with a weighted importance vector. The importance vector ensures that the loss at the last step has more importance than the previous steps. Our empirical evaluation shows that MSL significantly improves the stability of the training procedure and it thus also improves the accuracy of the overall system. Our proposed system outperforms MAML based low resource ASR system on various languages in terms of character error rates and stable training behavior.