Metraipolis › archive › dc_d7769427fa53

Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages — arXiv:2609.29798

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29798
License (as archived)
CC0-1.0
Archived
2026-10-08T04:27:46.869Z
SHA-256 of the archived text
2489d5a0ef5cafb699e60b891861ad2bfb2632d868afd4f6ab89922993b6f6e6
Stable URL of this page
https://metraipolis.com/documento/dc_d7769427fa53

How to cite

Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages — arXiv:2609.29798 — arXiv (en), https://arxiv.org/abs/2609.29798 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d7769427fa53 (Metraipolis archive dc_d7769427fa53, sha256 2489d5a0ef5cafb699e60b891861ad2bfb2632d868afd4f6ab89922993b6f6e6)
BibTeX
@misc{dcd7769427fa53,
  title = {Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages — arXiv:2609.29798},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29798},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d7769427fa53; sha256 2489d5a0ef5cafb699e60b891861ad2bfb2632d868afd4f6ab89922993b6f6e6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29798. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper presents an end-to-end study of automatic speech recognition (ASR) for adolescent health communication in three Ghanaian languages (Twi, Dagbani, and Ewe). The work proceeds in three connected stages; First, we benchmark five ASR systems (three language-specific Wav2Vec2 models and two multimodal LLMs, Gemma 3n and Gemma 4) on a general-domain Bible corpus and a Youth Adolescent Sexual and Reproductive Health (ASRH) Domain ASR dataset, using Character and Word Error Rate (CER, WER). Second, guided by the benchmark, we perform supervised domain adaptation: although Gemma 4 was the strongest zero-shot candidate, fine-tuning it proved computationally infeasible, so we pivoted to the compact Qwen3-ASR-0.6B, fine-tuned on a large Ghana Bible corpus (~90k samples) and evaluated strictly on held-out human-collected in-domain audio. Fine-tuning reduced WER on every language, most dramatically for Ewe (WER from 109.3% to 64.8%, a drop of 44.5 pp; CER from 65.1% to 24.9%). Third, we validate the work through KasaHealth, a live voice-first ASRH application deployed in all three languages, complemented by Senti-Check, a technical evaluation harness. KasaHealth was tested by 50 community respondents and achieved a 100% chat-approval rate, a 72% Good-or-Excellent translation rating, and a 92% would-recommend rate, while surfacing the domain gaps that most constrain real-world use. Across all three stages the evidence converges: for these languages the binding constraint is validated in-domain data, not model capability or computation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.29798 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T03:50:58.157Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).