mlsanityData to 13 Oct 2026

Improved Meta Learning for Low Resource Speech Recognition

arXiv 2205.06182 ↗First posted 11 May 2022cs.CL cs.LG cs.SDcited by 7

Not on the map. Why?

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.

Key facts. Cited by 7 papers in the map (data through 13 Oct 2026). Builds on 20 of its 24 references that are in the map. First posted on arXiv 11 May 2022.

Builds on

20 of 24 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,106
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,870
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,870
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,011
  6. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,366
  7. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,359
  8. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 500
  9. 2018How to train your MAMLcited by 306
  10. 2019Few-shot Video-to-Video Synthesiscited by 197
  11. 2018Meta-Learning for Low-Resource Neural Machine Translationcited by 105
  12. 2019End-to-end Text-to-speech for Low-resource Languages by Cross-Lingual Transfer Learningcited by 30
8 more
  1. 2019Meta Learning for End-to-End Low-Resource Speech Recognitioncited by 29
  2. 2020Learning Fast Adaptation on Cross-Accented Speech Recognitioncited by 28
  3. 2018Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languagescited by 26
  4. 2017A Simple Neural Attentive Meta-Learnercited by 22
  5. 2019Speaker Adaptive Training using Model Agnostic Meta-Learningcited by 8
  6. 2020Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairscited by 8
  7. 2021DEEPF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signalscited by 7
  8. 2018Learning to adapt: a meta-learning approach for speaker adaptationcited by 6

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3; 2025: 1.

7 papers.

  1. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  2. 2023A Novel Self-training Approach for Low-resource Speech Recognitioncited by 7
  3. 2024SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognitioncited by 4
  4. 2024Meta-Learning in Audio and Speech Processing: An End to End Comprehensive Reviewcited by 2
  5. 2023PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognitioncited by 1
  6. 2025Robust Cross-Etiology and Speaker-Independent Dysarthric Speech Recognitioncited by 1
  7. 2024Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learningcited by 0