# AfriNames: Most ASR models "butcher" African Names

arXiv: https://arxiv.org/abs/2306.00253 · HTML: https://mlsanity.com/paper/2306.00253/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 84 references that are in the map.
- First posted on arXiv 1 Jun 2023.

## Builds on (most cited first, 30 of 34)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [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)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [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)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [Not Enough Data? Deep Learning to the Rescue!](https://mlsanity.com/paper/1911.03118/) (2019)
- [MasakhaNER: Named Entity Recognition for African Languages](https://mlsanity.com/paper/2103.11811/) (2021)
- [Data Augmentation for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1705.00440/) (2017)
- [SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network](https://mlsanity.com/paper/2104.02133/) (2021)
- [Towards Building ASR Systems for the Next Billion Users](https://mlsanity.com/paper/2111.03945/) (2021)
- [Domain Adversarial Training for Accented Speech Recognition](https://mlsanity.com/paper/1806.02786/) (2018)
- [MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition](https://mlsanity.com/paper/2210.12391/) (2022)
- [Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model](https://mlsanity.com/paper/1712.01541/) (2017)
- [Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages](https://mlsanity.com/paper/2012.12121/) (2020)
- [Multi-Modal Data Augmentation for End-to-End ASR](https://mlsanity.com/paper/1803.10299/) (2018)
- [AI4D -- African Language Program](https://mlsanity.com/paper/2104.02516/) (2021)
- [Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Users](https://mlsanity.com/paper/2104.13083/) (2021)
- [Building African Voices](https://mlsanity.com/paper/2207.00688/) (2022)
- [OkwuGb'e: End-to-End Speech Recognition for Fon and Igbo](https://mlsanity.com/paper/2103.07762/) (2021)
- [Accented Speech Recognition: A Survey](https://mlsanity.com/paper/2104.10747/) (2021)
- [AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks for End-to-end Speech Recognition](https://mlsanity.com/paper/1911.11935/) (2019)
- [End-to-end model for named entity recognition from speech without paired training data](https://mlsanity.com/paper/2204.00803/) (2022)

## Built on by (most cited first, 7 of 7)

- [Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead](https://mlsanity.com/paper/2505.21315/) (2025)
- [Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond](https://mlsanity.com/paper/2502.03945/) (2025)
- [Performant ASR Models for Medical Entities in Accented Speech](https://mlsanity.com/paper/2406.12387/) (2024)
- [AccentFold: A Journey through African Accents for Zero-Shot ASR Adaptation to Target Accents](https://mlsanity.com/paper/2402.01152/) (2024)
- [Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Review](https://mlsanity.com/paper/2510.01145/) (2025)
- [Towards Open-Ended Discovery for Low-Resource NLP](https://mlsanity.com/paper/2510.01220/) (2025)
- [Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech](https://mlsanity.com/paper/2609.11786/) (2026)

## Abstract (arXiv)

Useful conversational agents must accurately capture named entities to minimize error for downstream tasks, for example, asking a voice assistant to play a track from a certain artist, initiating navigation to a specific location, or documenting a laboratory result for a patient. However, where named entities such as ``Ukachukwu`` (Igbo), ``Lakicia`` (Swahili), or ``Ingabire`` (Rwandan) are spoken, automatic speech recognition (ASR) models' performance degrades significantly, propagating errors to downstream systems. We model this problem as a distribution shift and demonstrate that such model bias can be mitigated through multilingual pre-training, intelligent data augmentation strategies to increase the representation of African-named entities, and fine-tuning multilingual ASR models on multiple African accents. The resulting fine-tuned models show an 81.5% relative WER improvement compared with the baseline on samples with African-named entities.