# Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages

arXiv: https://arxiv.org/abs/2012.12121 · HTML: https://mlsanity.com/paper/2012.12121/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 30 of 30)

- [End-to-end Speech Translation via Cross-modal Progressive Training](https://mlsanity.com/paper/2104.10380/) (2021)
- [Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults](https://mlsanity.com/paper/2309.07927/) (2023)
- [FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning](https://mlsanity.com/paper/2207.00555/) (2022)
- [Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition](https://mlsanity.com/paper/2101.06699/) (2021)
- [Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model](https://mlsanity.com/paper/2112.07254/) (2021)
- [Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation](https://mlsanity.com/paper/2204.02470/) (2022)
- [Phoneme Segmentation Using Self-Supervised Speech Models](https://mlsanity.com/paper/2211.01461/) (2022)
- [Automatic recognition of suprasegmentals in speech](https://mlsanity.com/paper/2108.01122/) (2021)
- [AfriNames: Most ASR models "butcher" African Names](https://mlsanity.com/paper/2306.00253/) (2023)
- [A Novel Self-training Approach for Low-resource Speech Recognition](https://mlsanity.com/paper/2308.05269/) (2023)
- [Decoupling recognition and transcription in Mandarin ASR](https://mlsanity.com/paper/2108.01129/) (2021)
- [Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation](https://mlsanity.com/paper/2207.03334/) (2022)
- [Huqariq: A Multilingual Speech Corpus of Native Languages of Peru for Speech Recognition](https://mlsanity.com/paper/2207.05498/) (2022)
- [Applying wav2vec2 for Speech Recognition on Bengali Common Voices Dataset](https://mlsanity.com/paper/2209.06581/) (2022)
- [Automatic Speech Recognition (ASR) for the Diagnosis of pronunciation of Speech Sound Disorders in Korean children](https://mlsanity.com/paper/2403.08187/) (2024)
- [Efficient Finetuning for Dimensional Speech Emotion Recognition in the Age of Transformers](https://mlsanity.com/paper/2503.03756/) (2025)
- [DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model](https://mlsanity.com/paper/2306.01303/) (2023)
- [DualVoice: Speech Interaction that Discriminates between Normal and Whispered Voice Input](https://mlsanity.com/paper/2208.10499/) (2022)
- [Political corpus creation through automatic speech recognition on EU debates](https://mlsanity.com/paper/2304.08137/) (2023)
- [Unsupervised speech intelligibility assessment with utterance level alignment distance between teacher and learner Wav2Vec-2.0 representations](https://mlsanity.com/paper/2306.08845/) (2023)
- [Toward Leveraging Pre-Trained Self-Supervised Frontends for Automatic Singing Voice Understanding Tasks: Three Case Studies](https://mlsanity.com/paper/2306.12714/) (2023)
- [End to end Hindi to English speech conversion using Bark, mBART and a finetuned XLSR Wav2Vec2](https://mlsanity.com/paper/2401.06183/) (2024)
- [Automatic Speech Recognition Advancements for Indigenous Languages of the Americas](https://mlsanity.com/paper/2404.08368/) (2024)
- [Semantically Corrected Amharic Automatic Speech Recognition](https://mlsanity.com/paper/2404.13362/) (2024)
- [Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers](https://mlsanity.com/paper/2104.10328/) (2021)
- [Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models](https://mlsanity.com/paper/2210.06936/) (2022)
- [Combining Contrastive and Non-Contrastive Losses for Fine-Tuning Pretrained Models in Speech Analysis](https://mlsanity.com/paper/2211.01964/) (2022)
- [Transcription and translation of videos using fine-tuned XLSR Wav2Vec2 on custom dataset and mBART](https://mlsanity.com/paper/2403.00212/) (2024)
- [Poem Meter Classification of Recited Arabic Poetry: Integrating High-Resource Systems for a Low-Resource Task](https://mlsanity.com/paper/2504.12172/) (2025)
- [Mitigating Structural Noise in Low-Resource S2TT: An Optimized Cascaded Nepali-English Pipeline with Punctuation Restoration](https://mlsanity.com/paper/2602.21647/) (2026)

## Abstract (arXiv)

There are several domains that own corresponding widely used feature extractors, such as ResNet, BERT, and GPT-x. These models are usually pre-trained on large amounts of unlabeled data by self-supervision and can be effectively applied to downstream tasks. In the speech domain, wav2vec2.0 starts to show its powerful representation ability and feasibility of ultra-low resource speech recognition on the Librispeech corpus, which belongs to the audiobook domain. However, wav2vec2.0 has not been examined on real spoken scenarios and languages other than English. To verify its universality over languages, we apply pre-trained models to solve low-resource speech recognition tasks in various spoken languages. We achieve more than 20% relative improvements in six languages compared with previous work. Among these languages, English achieves a gain of 52.4%. Moreover, using coarse-grained modeling units, such as subword or character, achieves better results than fine-grained modeling units, such as phone or letter.