# AfriSwitch: A Benchmark for In-the-Wild African Code-Switched Speech Recognition

arXiv: https://arxiv.org/abs/2608.26434 · HTML: https://mlsanity.com/paper/2608.26434/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [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)
- [GLUECoS : An Evaluation Benchmark for Code-Switched NLP](https://mlsanity.com/paper/2004.12376/) (2020)
- [LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation](https://mlsanity.com/paper/2005.04322/) (2020)
- [YODAS: Youtube-Oriented Dataset for Audio and Speech](https://mlsanity.com/paper/2406.00899/) (2024)
- [The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results](https://mlsanity.com/paper/2007.05916/) (2020)
- [AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR](https://mlsanity.com/paper/2310.00274/) (2023)
- [Challenges and Limitations with the Metrics Measuring the Complexity of Code-Mixed Text](https://mlsanity.com/paper/2106.10123/) (2021)
- [SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset](https://mlsanity.com/paper/2506.00087/) (2025)
- [Building a Unified Code-Switching ASR System for South African Languages](https://mlsanity.com/paper/1807.10949/) (2018)
- [Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching](https://mlsanity.com/paper/2311.15077/) (2023)
- [PIER: A Novel Metric for Evaluating What Matters in Code-Switching](https://mlsanity.com/paper/2501.09512/) (2025)
- [WAXAL: A Large-Scale Multilingual African Language Speech Corpus](https://mlsanity.com/paper/2602.02734/) (2026)
- [Attention-Guided Adaptation for Code-Switching Speech Recognition](https://mlsanity.com/paper/2312.08856/) (2023)
- [Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer](https://mlsanity.com/paper/2306.08753/) (2023)
- [Adapting OpenAI's Whisper for Speech Recognition on Code-Switch Mandarin-English SEAME and ASRU2019 Datasets](https://mlsanity.com/paper/2311.17382/) (2023)
- [Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding](https://mlsanity.com/paper/2412.16507/) (2024)
- [The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages](https://mlsanity.com/paper/2505.20564/) (2025)
- [Voice of a Continent: Mapping Africa's Speech Technology Frontier](https://mlsanity.com/paper/2505.18436/) (2025)
- [AfriSpeech-MultiBench: A Verticalized Multidomain Multicountry Benchmark Suite for African Accented English ASR](https://mlsanity.com/paper/2511.14255/) (2025)

## Abstract (arXiv)

Code-switching is pervasive in bilingual African conversation, yet most ASR systems assume monolingual input and are evaluated on curated monolingual benchmarks. We present AfriSwitch, a 61.36-hour human-transcribed benchmark of in-the-wild code-switched speech spanning 16 African languages and language varieties, released with switch-level English span tags, perutterance Code-Mixing Index (CMI), and switch-point counts. Corpus statistics show that mixing behaviour varies widely across African languages along two largely independent axes: how often speakers alternate, and how balanced the mixture is. No single scalar captures how code-switched a language is. Benchmarking five open and commercial multilingual ASR systems zero-shot yields word error rates far above published monolingual figures for the same languages, with the best system averaging 35.93% WER and no system falling below 24% on any language. Africa-targeted training, not model scale or nominal language coverage, best predicts performance.