AfriVox-v2: A Domain-Verticalized Benchmark for In-the-Wild African Speech Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909014416162816 |
|---|---|
| author | Awobade, Busayo Ashungafac, Gabrial Zencha Olatunji, Tobi |
| author_facet | Awobade, Busayo Ashungafac, Gabrial Zencha Olatunji, Tobi |
| contents | Recent large language models (LLMs) show strong speech recognition and translation capabilities for high-resource languages. However, African languages remain dramatically underrepresented in benchmarks, limiting their practical use in low-resource settings. While early benchmarks tested African languages and accents, they lacked exhaustive real-world noise and granular domain evaluations. We present AfriVox-v2, a comprehensive benchmark designed to test speech models under realistic African deployment conditions. AfriVox-v2 introduces "in the wild" unscripted audio for all supported languages. We also introduce strict domain verticalization, evaluating model accuracy across ten sectors including government, finance, health, and agriculture and conducting targeted tests on numbers and named entities. Finally, we benchmark a new generation of speech models, including Sahara-v2, Gemini 3 Flash, and the Omnilingual CTC models. Our results expose the true generalization gap of modern speech models in specialized, noisy African contexts and provide a reliable blueprint for developers building localized voice AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03590 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AfriVox-v2: A Domain-Verticalized Benchmark for In-the-Wild African Speech Recognition Awobade, Busayo Ashungafac, Gabrial Zencha Olatunji, Tobi Computation and Language Sound Recent large language models (LLMs) show strong speech recognition and translation capabilities for high-resource languages. However, African languages remain dramatically underrepresented in benchmarks, limiting their practical use in low-resource settings. While early benchmarks tested African languages and accents, they lacked exhaustive real-world noise and granular domain evaluations. We present AfriVox-v2, a comprehensive benchmark designed to test speech models under realistic African deployment conditions. AfriVox-v2 introduces "in the wild" unscripted audio for all supported languages. We also introduce strict domain verticalization, evaluating model accuracy across ten sectors including government, finance, health, and agriculture and conducting targeted tests on numbers and named entities. Finally, we benchmark a new generation of speech models, including Sahara-v2, Gemini 3 Flash, and the Omnilingual CTC models. Our results expose the true generalization gap of modern speech models in specialized, noisy African contexts and provide a reliable blueprint for developers building localized voice AI. |
| title | AfriVox-v2: A Domain-Verticalized Benchmark for In-the-Wild African Speech Recognition |
| topic | Computation and Language Sound |
| url | https://arxiv.org/abs/2605.03590 |