* means equal contribution, shared co-first authorship.
Please see my Google Scholar for a complete list of publications.
Under Review Works
- Aligning Stuttered-Speech Research with End-User Needs: Scoping Review, Survey, and Guidelines. HO Toyin, M Apampa, T Samuel, H Alblooshi, Z Talat, Z Yue, H Aldarmaki
- What Counts as an Error? Dual-Reference Benchmarking for Atypical ASR. HO Toyin, S Umesh, H Aldarmaki.
Selected Conference Papers
- Gretino: a Greek and Latin Dataset to Benchmark Retrieval Systems in Classical Languages. HO Toyin, F Iezzi, E Scapini, G Federico, G Puccetti. LREC 2026
- Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study. HO Toyin, S Magdy, H Aldarmaki. LREC 2026
- ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis. HO Toyin*,RF Marew, H Alblooshi, S Magdy, H Aldarmaki. Interspeech 2025
- Dialectal Coverage And Generalization in Arabic Speech Recognition. A Djanibekov*,HO Toyin*, R Alshalan, A Alitr, H Aldarmaki. ACL 2025
- Where Are We? Evaluating LLM Performance on African Languages. I Adebara, HO Toyin, NT Ghebremichael, AR Elmadany, M Abdul-Mageed. ACL 2025
- Infant Cry Detection Using Causal Temporal Representation. M Fu, D Li, ...,HO Toyin, ..., H Aldarmaki. ICASSP 2025
- Exploring the Limitations of Detecting Machine-Generated Text. J Doughman, OM Afzal, HO Toyin, S Shehata, P Nakov, Z Talat. COLING 2025
- STTATTS: Unified Speech-To-Text And Text-To-Speech Model. HO Toyin, H Li, H Aldarmaki. EMNLP 2024 findings.
- PolyWER: A Holistic Evaluation Framework for Code-Switched Speech Recognition. K Kadaoui, M Ali, HO Toyin, I Mohammed, H Aldarmaki. EMNLP 2024 findings.
- 🏆ArTST: Arabic Text and Speech Transformer.HO Toyin*, A Djanibekov*, A Kulkarni, H Aldarmaki. ArabicNLP 2023. Best Paper Award.
Presentations
- Research Presentation: Arabic Multimodal Language Modeling. ISTI-CNR 2025.