# Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning

arXiv: https://arxiv.org/abs/2208.03067 · HTML: https://mlsanity.com/paper/2208.03067/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 44 references that are in the map.
- First posted on arXiv 5 Aug 2022.

## Builds on (most cited first, 17 of 17)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [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)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [Hybrid Autoregressive Transducer (hat)](https://mlsanity.com/paper/2003.07705/) (2020)
- [BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2109.13226/) (2021)
- [Multilingual Speech Recognition With A Single End-To-End Model](https://mlsanity.com/paper/1711.01694/) (2017)
- [FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization](https://mlsanity.com/paper/2010.11148/) (2020)
- [Scaling End-to-End Models for Large-Scale Multilingual ASR](https://mlsanity.com/paper/2104.14830/) (2021)
- [Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages](https://mlsanity.com/paper/1806.05059/) (2018)
- [Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning](https://mlsanity.com/paper/2110.00165/) (2021)
- [Sequence-based Multi-lingual Low Resource Speech Recognition](https://mlsanity.com/paper/1802.07420/) (2018)
- [Accented Speech Recognition: Benchmarking, Pre-training, and Diverse Data](https://mlsanity.com/paper/2205.08014/) (2022)
- [BembaSpeech: A Speech Recognition Corpus for the Bemba Language](https://mlsanity.com/paper/2102.04889/) (2021)
- [OkwuGb'e: End-to-End Speech Recognition for Fon and Igbo](https://mlsanity.com/paper/2103.07762/) (2021)
- [Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training](https://mlsanity.com/paper/1907.03064/) (2019)
- [Text Normalization for Low-Resource Languages of Africa](https://mlsanity.com/paper/2103.15845/) (2021)

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

- [MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages](https://mlsanity.com/paper/2305.13989/) (2023)
- [Africa-Centric Self-Supervised Pre-Training for Multilingual Speech Representation in a Sub-Saharan Context](https://mlsanity.com/paper/2404.02000/) (2024)
- [AfriNames: Most ASR models "butcher" African Names](https://mlsanity.com/paper/2306.00253/) (2023)
- [KinSPEAK: Improving speech recognition for Kinyarwanda via semi-supervised learning methods](https://mlsanity.com/paper/2308.11863/) (2023)
- [Benchmarking Automatic Speech Recognition Models for African Languages](https://mlsanity.com/paper/2512.10968/) (2025)
- [From a Multilingual Streaming ASR Backbone to Kenyan-Language Systems: Data-Centric Adaptation of Nemotron 3.5 for Kikuyu, Dholuo, and Kalenjin](https://mlsanity.com/paper/2607.18912/) (2026)

## Abstract (arXiv)

Almost none of the 2,000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages. We have experimented with two techniques which may provide pathways to large vocabulary speech recognition for African languages: multilingual modeling and self-supervised learning. We gathered available open source data and collected data for 15 languages, and trained experimental models using these techniques. Our results show that pooling the small amounts of data available in multilingual end-to-end models, and pre-training on unsupervised data can help improve speech recognition quality for many African languages.