Elamur Research⌕
☰
home / papers / 2026 / Automatic Extraction of Textual and Phonemic Complexity for French Cued Speech

Automatic Extraction of Textual and Phonemic Complexity for French Cued Speech

Summary

Cued Speech (CS) helps people with hearing loss read spoken language from the lips: handshapes placed at positions near the face separate phonemes that look the same on the mouth. Few resources exist for learning French CS. The VizLector project plans an online platform with automatically cued videos, and it needs a way to rank candidate texts by how hard they are to cue or decode.

The authors annotated the 200 texts of the Alector corpus with 41 features:

  • Readability features, taken mostly from the FABRA toolkit, covering length, lexical and syntactic properties.
  • Phonemic and CS-key features, produced with SPPAS, which handles phonetization and automatic generation of CS keys.

They then studied how these features correlate with one another. Readability measures were often strongly intercorrelated. Phonemic measures showed few such links, and the two families showed few links with each other. This suggests the phonemic and CS-key features capture information that standard readability metrics miss. The paper ends with a first, unsupervised model for choosing texts to record. It is an initial step toward grading French CS learning materials by difficulty.

Key points

  • Corpus: Alector, with 100 original texts and 100 human-simplified counterparts.
    • Half are literary and half scientific.
    • The texts target children aged 7–11.
    • They span five levels: IReST, CE1, CE2, CM1 and CM2.
  • Readability features: 31 in total. Of these, 30 come from FABRA (3 length-based, 23 lexical, 5 syntactic), selected from 509 available predictors, and 1 extra length variable was added. Values are averaged, except LEXdvrFLC.
  • Phonemic features: 10 variables computed with SPPAS v.4.29, including:
    • CS key counts;
    • transitions between side, cheekbone and throat positions;
    • CV and CC clusters;
    • glides (w, ɥ, j);
    • obligatory liaisons.
  • French CS inventory: 8 consonant handshapes and 5 vowel positions, plus a neutral handshape and position used during silences.
  • Related resources: AutoCS/TextCueS (open-source CS key generation) and the CLeLfPC corpus (4 hours of partly annotated CS recordings).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages · Natural language processing

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/2efggr7hkgst

@inproceedings{norre2026automatic,
  title = {{Automatic Extraction of Textual and Phonemic Complexity for French Cued Speech}},
  author = {Norré, Magali and Bigi, Brigitte and Gala, Núria and Drevet, Ludivine Javourey and François, Thomas},
  booktitle = {Proceedings of the Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026},
  year = {2026},
  doi = {10.63317/2efggr7hkgst},
  url = {https://doi.org/10.63317/2efggr7hkgst}
}

References

33 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Mélody Artaz. 2011. L’apprentissage de la Langue française Parlée Completée par les enfants sourds d’âge scolaire : Conception d’un loto LPC. Master’s thesis, Université Stendhal. find
  2. Brigitte Bigi. 2015. SPPAS - Multi-Lingual Approaches to the Automatic Annotation of Speech. The Phonetician. Journal of the International Society of Phonetic Sciences, 111:54–69. ↗
  3. Brigitte Bigi. 2023. An analysis of produced versus predicted French Cued Speech keys. In 10th Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics, pages 24–28, Poznań, Poland. find
  4. Liliane Kandel and Abraham Moles. 1958. Application de l’indice de Flesch à la langue française. Cahiers Etudes de Radio-Télévision, 19:253– 274. find
  5. Brigitte Bigi. 2025a. Bridging the Gap: Design and Evaluation of an Automated System for French Cued Speech. In Proceedings of the 8th International Conference on Natural Language and Speech Processing (ICNLSP-2025), pages 8– 18, Southern Denmark University, Odense, Denmark. Association for Computational Linguistics. find
  6. András Kornai. 2007. Mathematical Linguistics. Springer Science & Business Media. find
  7. Katsunori Kotani, Shota Ueda, Takehiko Yoshimi, and Hiroaki Nanjo. 2014. A Listenability Measuring Method for an Adaptive Computer-assisted Language Learning and Teaching System. In Proceedings of the 28th Pacific Asia Conference on Language, Information and Computing, pages 387–394. find
  8. Brigitte Bigi. 2025b. Spatial Analysis of Hand Positions in French Cued Speech (LfPC). In 16th International Conference on Linguistic Research and Applications, Paris, France. ↗
  9. Katsunori Kotani and Takehiko Yoshimi. 2017. Effectiveness of Linguistic and Learner Features for Listenability Measurement Using a Decision Tree Classifier. The Journal of Information and Systems in Education, 16(1):7–11. ↗
  10. Malika Charrad, Nadia Ghazzali, Véronique Boiteau, and Azam Niknafs. 2014. NbClust: An R Package for Determining the Relevant Number of Clusters in a Data Set. Journal of Statistical Software, 61(6):1–36. ↗
  11. Mélanie Lancien and Brigitte Bigi. 2025. French Cued Speech rhythm: first findings on the relationship between hand position and segments’ duration. In 11th Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science, Linguistics and Low Resourced Languages, Poznań, Poland. ↗
  12. R. Orin Cornett. 1967. Cued Speech. American Annals of the Deaf, 112(1):3–13. find
  13. Nicolas De Jay, Simon Papillon-Cavanagh, Catharina Olsen, Nehme El-Hachem, Gianluca Bontempi, and Benjamin Haibe-Kains. 2013. mRMRe: an R package for parallelized mRMR ensemble feature selection. Bioinformatics, 29(18):2365–2368. ↗
  14. Manuel Leitao, Elodie Venti, Thomas Sigiez, Christophe Laroche, Marie Perini, and Agnès Piquard-Kipffer. 2021. Projet LogilecSur: quelles stratégies enseignantes pour guider des élèves sourds vers l’autonomie en compréhension écrite? In IDEKI 2021 - 4ème colloque international Didactiques et métiers de l’humain, Pont-à-Mousson, France. find
  15. Chris Ding and Hanchuan Peng. 2005. Minimum Redundancy Feature Selection from Microarray Gene Expression Data. Journal of Bioinformatics and Computational Biology, 3(2):185–205. ↗
  16. Jacqueline Leybaert and Carol J. LaSasso. 2010. Cued Speech for Enhancing Speech Perception and First Language Development of Children With Cochlear Implants. Trends in Amplification, 14(2):96–112. ↗
  17. Rudolph Flesch. 1948. A New Readability Yardstick. Journal of Applied Psychology, 32(3):221–233. find
  18. Núria Gala, Brigitte Bigi, and Marie Bauer. 2024. Automatically Estimating Textual and Phonemic Complexity for Cued Speech: How to See the Sounds from French Texts. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1817– 1824, Torino, Italia. ELRA and ICCL. find
  19. Aïnizé Olhagaray. 2013. « Le Pirate Codeur » : Élaboration d’un matériel ludique visant à entraîner et automatiser le décodage de la Langue française Parlée Complétée (LPC) : à destination des enfants sourds ayant reçu une introduction tardive du code LPC. Master’s thesis, Université Bordeaux Segalen. find
  20. Ludivine Javourey-Drevet, Stéphane Dufau, Thomas François, Núria Gala, Jacques Ginestié, and Johannes C. Ziegler. 2022. Simplification of literary and scientific texts to improve reading fluency and comprehension in beginning readers of French. Applied Psycholinguistics, 43(2):485–512. find
  21. Lucía Ormaechea and Nikos Tsourakis. 2024. Automatic text simplification for French: model fine-tuning for simplicity assessment and simpler text generation. International Journal of Speech Technology, 27(4):957–976. ↗
  22. Minami Ozawa, Rodrigo Wilkens, Kaori Sugiyama, and Thomas François. 2024. Modéliser la facilité d’écoute en FLE: vaut-il mieux lire la transcription ou écouter le signal vocal ? In Elaine Jones, Robert Strom, and Susan Daniels. 1989. Evaluating the Success of Deaf Parents. American Annals of the Deaf, 134(5):312–316. 35èmes Journées d’études sur la Parole (JEP 2024) 31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024) 26ème Rencontre des étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL 2024), volume 1, pages 549– 566. ATALA & AFPC. find
  23. Gala, Núria and Tack, Anaïs and Javourey-Drevet, Ludivine and François, Thomas and Ziegler, Johannes C. 2020. Alector: A Parallel Corpus of Simplified French Texts with Alignments of Misreadings by Poor and Dyslexic Readers. ELRA. find
  24. Vital-Durand, François. 2011. International Reading Speed Texts IResT (French version). find
  25. Agnès Piquard-Kipffer. 2016. Un album numérique pour raconter une histoire avec un avatar narrateur. In XVIèmes rencontres internationales en orthophonie - Orthophonie et technologies innovantes, Paris, France. find
  26. R Core Team. 2021. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing. find
  27. Stéphane Rauzy, Grégoire Montcheuil, and Philippe Blache. 2014. MarsaTag, a tagger for French written texts and speech transcriptions. In Second Asian Pacific Corpus linguistics Conference, pages 220–220, Hong Kong, China. find
  28. Valérie Sabbagh. 2012a. Le Petit Clown 2 Le LPC pour les enfants : Entraînement et perfectionnement. ALPC, Paris, France. find
  29. Valérie Sabbagh. 2012b. Le Petit Clown Le LPC pour les enfants : L’imagier d’Agathe. ALPC, Paris, France. find
  30. Sanjana Sankar. 2024. Automatic recognition and generation of French Cued Speech using deep learning. Ph.D. thesis, Université Grenoble Alpes. ↗
  31. Rodrigo Wilkens, David Alfter, Xiaoou Wang, Alice Pintard, Anaïs Tack, Kevin P Yancey, and Thomas François. 2022. FABRA: French Aggregator-Based Readability Assessment toolkit. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1217–1233, Marseille, France. ELRA. find
  32. World Health Organization. 2021. World Report on Hearing. World Health Organization. ISBN: 978-92-4-002048-1. 9. find
  33. Language Resource References Brigitte Bigi, Maryvonne Zimmermann, and Carine André. 2022. CLeLfPC: a Large Open Multi-Speaker Corpus of French Cued Speech. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 987– 994, Marseille, France. ELRA. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/norre-2026-automatic-extraction-textual-phonemic-complexity/