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

arXiv:2608.26434v1 Announce Type: new Abstract: 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.

Related

• AfriVox-v2: A Domain-Verticalized Benchmark for In-the-Wild African Speech Recognition
• From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languages
• Sometin Beta Pass Notin (SBPN): Improving Multilingual ASR for Nigerian Languages via Knowledge Distillation
• DONDO: Open w2v-BERT Speech-Recognition Base Models for African Languages

Source: arXiv cs.CL | 2026-08-28