Publications and Presenations
Publications and Presenations
Le Ferrand, É., Hauser, C., Hartshorne, J., Prud'hommeaux, E. (2025). Faithful Transcription: Leveraging Bible Recordings to Improve ASR for Endangered Languages. Proceedings of the International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics.
Link to the paper
Le Ferrand, É., Jiang, B., Hartshorne, J., Prud'hommeaux, E. (2025). That doesn’t sound right: Evaluating speech transcription quality in field linguistics corpora. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics.
Scheppat, H., Hartshorne, J., Leddy, D., Le Ferrand, É., Prudhommeaux, E. (2025). Integrating diverse corpora for training endangered language machine translation systems. Proceedings of the 8th Workshop on Computational Methods for Endangered Languages (ComputEL-8)
Le Ferrand, É., Liu, Z., Arppe, A., Prud'hommeaux, E. (2024). Are modern neural ASR architectures robust for polysynthetic languages? Findings of The 2024 Conference on Empirical Methods in Natural Language Processing.
Allahsera T., Le Ferrand, É., Liu, Z., Homan, C., Prud'hommeaux, E. (2024) Leveraging Speech Data Diversity to Document Indigenous Heritage and Culture. Interspeech.
Liu, Z., Venkateswaran, N., Le Ferrand, É., Prud'hommeaux, E. (2024) How Important is a Language Model for Low-resource ASR?. Findings of The 62nd Annual Meeting of the Association for Computational Linguistics.
Le Ferrand, É. Low-Resource is not the only problem: Advancing Speech Recognition in Field Linguistics. (2024) Teanga seminar series.
Le Ferrand, É., Heaton, R., Prud'hommeaux, E. (2024) Investigating ASR model generalizability for documentation of Enenlhet. Proceedings of the 4th Workshop on NLP for Indigenous Languages of the Americas
Le Ferrand, É., Prud'hommeaux, E. (2024) Automatic Transcription of Grammaticality Judgements for Language Documentation. Proceedings of the Workshop on Computational Methods for Endangered Languages.
Le Ferrand, É., Claudel P., Dong R., Lecouteux, B., Gonçalves-Teixeira, D., Havard, W.N., Schang E. (2023) Outiller la documentation des langues créoles, GdR LIFT.
Le Ferrand, É. (2023). Low-resource is not the only problem: Exploring ASR for Field linguistics. CL/NLP colloquium Brandeis University.
Le Ferrand, É. (2023). Bridging Skills and Enabling Dialogue between Computer Science and Documentary Linguistics. The UB Creolist Workshop
Garnier, M., Le Ferrand, É., Ringeval, F. (2023). Verbal and nonverbal feedback signals in response to increasing levels of miscommunication. In Interspeech 2023
Le Ferrand, É., Henri, F., Lecouteux, B., Schang, E. (2023). Application of Speech Processes for the Documentation of Kréyòl Gwadloupéyen. In Field Matters 2023
Le Ferrand, É. (2023).Du linguiste au TAListe : La reconnaissance de la parole pour aider la transcription de données créoles. Contact de langues et de lultures dans les espaces francophones (Colef 2023)
Le Ferrand, É. (2023). Leveraging Speech Recognition for Interactive Transcription in Australian Aboriginal Communities. PhD dissertation
Le Ferrand, É. (2022). TAL sur le terrain: Application de systèmes reconnaissance de la parole dans un contexte Indigène. Séminaires de spécialité Industrie de la langue
Le Ferrand, É., Bird, S., Besacier, L. (2022). Fashioning Local Designs from Generic Speech Technologies in an Australian Aboriginal Community. In COLING 2022
Le Ferrand, É., Bird, S., Besacier, L. (2022). Learning From Failure: Technology for Data Capture in an Australian Aboriginal Community. In ACL 2022
Le Ferrand, É. (2021) Leveraging Speech Recognition Methods for Interactive Transcription in Australian Aboriginal Communities. Linguistics seminar at the University of Western Australia.
Le Ferrand, É., Bird, S., Besacier, L. (2021). Spoken Term Detection Methods for sparse transcription in very low-resource settings. In ALTA 2021
Le Ferrand, É., Bird, S., Besacier, L. (2021). Collaborative transcription in Australian Aboriginal communities. In ICLDC 2021
Le Ferrand, É., Bird, S., Besacier, L. (2020). Enabling Interactive Transcription in an Indigenous Communitý. In COLING 2020
Boito, M. Z., Havard, W., Garnerin, M., Le Ferrand, É., Besacier, L. (2020). MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the Bible. In LREC 2020.