mlsanityData to 14 Oct 2026

Exploiting Adapters for Cross-lingual Low-resource Speech Recognition

arXiv 2105.11905 ↗First posted 18 May 2021cs.CL cs.SD eess.AScited by 35

Not on the map. Why?

Abstract (arXiv)

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition models can easily overfit. In this paper, we propose to use adapters to investigate the performance of multiple adapters for parameter-efficient cross-lingual speech adaptation. Based on our previous MetaAdapter that implicitly leverages adapters, we propose a novel algorithms called SimAdapter for explicitly learning knowledge from adapters. Our algorithm leverages adapters which can be easily integrated into the Transformer structure.MetaAdapter leverages meta-learning to transfer the general knowledge from training data to the test language. SimAdapter aims to learn the similarities between the source and target languages during fine-tuning using the adapters. We conduct extensive experiments on five-low-resource languages in Common Voice dataset. Results demonstrate that our MetaAdapter and SimAdapter methods can reduce WER by 2.98% and 2.55% with only 2.5% and 15.5% of trainable parameters compared to the strong full-model fine-tuning baseline. Moreover, we also show that these two novel algorithms can be integrated for better performance with up to 3.55% relative WER reduction.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). Builds on 38 of its 58 references that are in the map. First posted on arXiv 18 May 2021.

Builds on

38 of 58 references.

References · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  7. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  8. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  9. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  10. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  11. 2019Cross-lingual Language Model Pretrainingcited by 1,090
  12. 2018On First-Order Meta-Learning Algorithmscited by 1,018
26 more
  1. 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 788
  2. 2019On the Cross-lingual Transferability of Monolingual Representationscited by 578
  3. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  4. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 501
  5. 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 340
  6. 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 257
  7. 2018Meta-Learning: A Surveycited by 256
  8. 2019Simple, Scalable Adaptation for Neural Machine Translationcited by 242
  9. 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 211
  10. 2020Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameterscited by 110
  11. 2019Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Modelcited by 93
  12. 2017Multilingual Speech Recognition With A Single End-To-End Modelcited by 87
  13. 2020Learning from Task Descriptionscited by 78
  14. 2021Scaling End-to-End Models for Large-Scale Multilingual ASRcited by 61
  15. 2018Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytescited by 54
  16. 2020Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognitioncited by 35
  17. 2018Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modelingcited by 34
  18. 2019Meta Learning for End-to-End Low-Resource Speech Recognitioncited by 29
  19. 2019Massively Multilingual Adversarial Speech Recognitioncited by 28
  20. 2021Learning to Generate Task-Specific Adapters from Task Descriptioncited by 28
  21. 2018Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languagescited by 26
  22. 2020Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Modelcited by 24
  23. 2020Meta-Learning for Few-Shot NMT Adaptationcited by 20
  24. 2020Language-agnostic Multilingual Modelingcited by 17
  25. 2020Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognitioncited by 15
  26. 2021Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matchingcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 8; 2024: 13; 2025: 3; 2026: 3.

35 papers.

Sort:

By area:

  1. 2023Modular Deep Learningcited by 83
  2. 2023FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learningcited by 70
  3. 2024ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasetscited by 27
  4. 2023Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languagescited by 20
  5. 2022CHAPTER: Exploiting Convolutional Neural Network Adapters for Self-supervised Speech Modelscited by 13
  6. 2021Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0cited by 12
  7. 2022Boosting Cross-Domain Speech Recognition with Self-Supervisioncited by 10
  8. 2022Adaptive multilingual speech recognition with pretrained modelscited by 9
  9. 2023Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learningcited by 9
  10. 2023BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognitioncited by 9
  11. 2024C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learningcited by 8
  12. 2021Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASRcited by 7
23 more
  1. 2022Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognitioncited by 7
  2. 2022Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processingcited by 7
  3. 2024How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenariocited by 5
  4. 2025Improving Cross-Lingual Phonetic Representation of Low-Resource Languages Through Language Similarity Analysiscited by 5
  5. 2024Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASRcited by 4
  6. 2024Progressive unsupervised domain adaptation for ASR using ensemble models and multi-stage trainingcited by 4
  7. 2023Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognitioncited by 3
  8. 2024Efficient Adapter Tuning of Pre-trained Speech Models for Automatic Speaker Verificationcited by 3
  9. 2024ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Taskscited by 3
  10. 2023Language-universal phonetic encoder for low-resource speech recognitioncited by 2
  11. 2024AdaptGCD: Multi-Expert Adapter Tuning for Generalized Category Discoverycited by 2
  12. 2022Damage Control During Domain Adaptation for Transducer Based Automatic Speech Recognitioncited by 1
  13. 2024CMULAB: An Open-Source Framework for Training and Deployment of Natural Language Processing Modelscited by 1
  14. 2024UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognitioncited by 1
  15. 2025UniPET-SPK: A Unified Framework for Parameter-Efficient Tuning of Pre-trained Speech Models for Robust Speaker Verificationcited by 1
  16. 2026Sequential Adapter Stacking for Cross-Lingual Low-Resource ASRcited by 1
  17. 2023Audio-AdapterFusion: A Task-ID-free Approach for Efficient and Non-Destructive Multi-task Speech Recognitioncited by 0
  18. 2024Configurable Multilingual ASR with Speech Summary Representationscited by 0
  19. 2024Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASRcited by 0
  20. 2024Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learningcited by 0
  21. 2025Cross-lingual Embedding Clustering for Hierarchical Softmax in Low-Resource Multilingual Speech Recognitioncited by 0
  22. 2026Which Languages Transfer Best to Warlpiri? A Similarity-Based Study for Low-Resource ASRcited by 0
  23. 2026Automatic Speech Recognition for Low-Resource Sinhala: A Critical Review of Methods, Challenges, and Future Directionscited by 0