# Brazilian Portuguese Speech Recognition Using Wav2vec 2.0

arXiv: https://arxiv.org/abs/2107.11414 · HTML: https://mlsanity.com/paper/2107.11414/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 37 references that are in the map.
- First posted on arXiv 23 Jul 2021.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Adaptive Input Representations for Neural Language Modeling](https://mlsanity.com/paper/1809.10853/) (2018)

## Built on by (most cited first, 6 of 6)

- [ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion](https://mlsanity.com/paper/2204.00618/) (2022)
- [CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese](https://mlsanity.com/paper/2110.15731/) (2021)
- [Domain Specific Wav2vec 2.0 Fine-tuning For The SE&R 2022 Challenge](https://mlsanity.com/paper/2207.14418/) (2022)
- [A Large Dataset of Spontaneous Speech with the Accent Spoken in S~ao Paulo for Automatic Speech Recognition Evaluation](https://mlsanity.com/paper/2409.15350/) (2024)
- [CAM~OES: A Comprehensive Automatic Speech Recognition Benchmark for European Portuguese](https://mlsanity.com/paper/2508.19721/) (2025)
- [Bringing NURC/SP to Digital Life: the Role of Open-source Automatic Speech Recognition Models](https://mlsanity.com/paper/2210.07852/) (2022)

## Abstract (arXiv)

Deep learning techniques have been shown to be efficient in various tasks, especially in the development of speech recognition systems, that is, systems that aim to transcribe an audio sentence in a sequence of written words. Despite the progress in the area, speech recognition can still be considered difficult, especially for languages lacking available data, such as Brazilian Portuguese (BP). In this sense, this work presents the development of an public Automatic Speech Recognition (ASR) system using only open available audio data, from the fine-tuning of the Wav2vec 2.0 XLSR-53 model pre-trained in many languages, over BP data. The final model presents an average word error rate of 12.4% over 7 different datasets (10.5% when applying a language model). According to our knowledge, the obtained error is the lowest among open end-to-end (E2E) ASR models for BP.