# VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining

arXiv: https://arxiv.org/abs/2505.21527 · HTML: https://mlsanity.com/paper/2505.21527/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [FunASR: A Fundamental End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2305.11013/) (2023)
- [Zipformer: A faster and better encoder for automatic speech recognition](https://mlsanity.com/paper/2310.11230/) (2023)
- [Pruned RNN-T for fast, memory-efficient ASR training](https://mlsanity.com/paper/2206.13236/) (2022)
- [GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement](https://mlsanity.com/paper/2406.11546/) (2024)
- [Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic Compute](https://mlsanity.com/paper/2306.06672/) (2023)
- [MelHuBERT: A simplified HuBERT on Mel spectrograms](https://mlsanity.com/paper/2211.09944/) (2022)
- [Speech Pre-training with Acoustic Piece](https://mlsanity.com/paper/2204.03240/) (2022)
- [Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training](https://mlsanity.com/paper/2206.10125/) (2022)
- [Anatomy of Industrial Scale Multilingual ASR](https://mlsanity.com/paper/2404.09841/) (2024)
- [Fast and parallel decoding for transducer](https://mlsanity.com/paper/2211.00484/) (2022)
- [Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2309.13860/) (2023)
- [Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation](https://mlsanity.com/paper/2306.08920/) (2023)
- [k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2411.17100/) (2024)
- [CTCBERT: Advancing Hidden-unit BERT with CTC Objectives](https://mlsanity.com/paper/2210.08603/) (2022)
- [Biased Self-supervised learning for ASR](https://mlsanity.com/paper/2211.02536/) (2022)

## Built on by (most cited first, 3 of 3)

- [Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis](https://mlsanity.com/paper/2601.13802/) (2026)
- [ViMedCSS: A Vietnamese Medical Code-Switching Speech Dataset & Benchmark](https://mlsanity.com/paper/2602.12911/) (2026)
- [NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task](https://mlsanity.com/paper/2609.27086/) (2026)

## Abstract (arXiv)

Automatic speech recognition (ASR) has made remarkable progress but heavily relies on large-scale labeled data, which is scarce for low-resource languages like Vietnamese. While existing systems such as Whisper, USM, and MMS achieve promising performance, their efficacy remains inadequate in terms of training costs, latency, and accessibility. To address these issues, we propose VietASR, a novel ASR training pipeline that leverages vast amounts of unlabeled data and a small set of labeled data. Through multi-iteration ASR-biased self-supervised learning on a large-scale unlabeled dataset, VietASR offers a cost-effective and practical solution for enhancing ASR performance. Experiments demonstrate that pre-training on 70,000-hour unlabeled data and fine-tuning on merely 50-hour labeled data yield a lightweight but powerful ASR model. It outperforms Whisper Large-v3 and commercial ASR systems on real-world data. Our code and models will be open-sourced to facilitate research in low-resource ASR.