Speech technology remains out of reach for most of the 2,300+ languages in Africa. We present the first systematic assessment of large-scale synthetic voice corpora for African ASR. We apply a three-step process: LLM-driven text creation, TTS voice synthesis, and ASR fine-tuning. Eight out of ten languages for which we create synthetic text achieved readability scores above 5 out of 7. We evaluated ASR improvement for three (Hausa, Dholuo, Chichewa) and created more than 2,500 hours of synthetic voice data at below 1% of the cost of real data. W2v-BERT 2.0 speech encoder fine-tuned on 250h real and 250h synthetic data in Hausa matched a 500h real-data-only baseline, while 579h real and 450h to 993h synthetic data created the best performance. We also present gender-disaggregated ASR performance evaluation. For very low-resource languages, gains varied: Chichewa WER improved by ~6.5% with a 1:2 real-to-synthetic ratio; a 1:1 ratio for Dholuo showed similar improvements on some evaluation data, but not on others. Inves- tigating intercoder reliability, ASR errors and evaluation datasets revealed the need for more robust reviewer protocols and more accurate evaluation data. All data and models are publicly released to invite further work to improve synthetic data for African languages.

Text generation may require the pluralization of nouns, such as in context-sensitive user interfaces and in natural language generation more broadly. While this has been solved for the widely-used languages, this is still a challenge for the languages in the Bantu language family. Pluralization results obtained for isiZulu and Runyankore showed there were similarities in approach, including the need to combine syntax with semantics, despite belonging to different language zones. This suggests that bootstrapping and generalizability might be feasible. We investigated this systematically for seven languages across three different Guthrie language zones. The first outcome is that Meinhof’s 1948 specification of the noun classes are indeed inadequate for computational purposes for all examined languages, due to non-determinism in prefixes, and we thus redefined the characteristic noun class tables of 29 noun classes into 53. The second main result is that the generic pluralizer achieved over 93% accuracy in coverage testing and over 94% on a random sample. This is comparable to the language-specific isiZulu and Runyankore pluralizers.

Natural Language Generation (NLG) can be used to generate personalized health information, which is especially useful when provided in one’s own language. However, the NLG technique widely used in different domains and languages—templates—was shown to be inapplicable to Bantu languages, due to their characteristic agglutinative structure. We present here our use of the grammar engine NLG technique to generate text in Runyankore, a Bantu language indigenous to Uganda. Our grammar engine adds to previous work in this field with new rules for cardinality constraints, prepositions in roles, the passive, and phonological conditioning. We evaluated the generated text with linguists and non-linguists, who regarded most text as grammatically correct and understandable; and over 60% of them regarded all the text generated by our system to have been authored by a human being.

There are many domain-specific and language-specific NLG systems, of which it may be possible to adapt to related domains and languages. The languages in the Bantu language family have their own set of features distinct from other major groups, which therefore severely limits the options to bootstrap an NLG system from existing ones. We present here our first proof-of-concept application for knowledge-to-text NLG as a plugin to the Protege 5.x ontology development system, tailored to Runyankore, a Bantu language indigenous to Uganda. It comprises a basic annotation model for linguistic information such as noun class, an implementation of existing verbalisation rules and a CFG for verbs, and a basic interface for data entry.