@inproceedings{norre-etal-2026-automatic,
title = "Automatic Extraction of Textual and Phonemic Complexity for {F}rench Cued Speech",
author = "Norr{\'e}, Magali and
Bigi, Brigitte and
Gala, N{\'u}ria and
Drevet, Ludivine Javourey and
Fran{\c{c}}ois, Thomas",
editor = "Shardlow, Matthew and
Fran{\c{c}}ois, Thomas and
Amaro, Raquel and
Baptista, Jorge and
Cardon, R{\'e}mi and
Ribeiro, Eug{\'e}nio and
Saggion, Horacio and
Stodden, Regina and
Todirascu, Amalia and
Wilkens, Rodrigo",
booktitle = "Proceedings of the Joint Workshop on Readability and Text Simplification ({READI}x{TSAR}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.readi-1.5/",
doi = "10.63317/2efggr7hkgst",
pages = "61--73",
abstract = "This article presents the results of an analysis of a written corpus with the view of automatically generating it in French Cued Speech (CS). CS is a communication system developed for people with hearing impairment to complement speech reading at the phonetic level using hands. This visual communication mode uses handshapes in different positions near the face in combination with the mouthshape (called `cues' or `keys') to make the phonemes of spoken language look different from each other. Despite many studies demonstrating its benefits, there are few resources available for learning and practicing it, especially in French. As part of a wider project aimed at creating an online learning platform with automatically generated videos using an augmented reality system displaying a virtual coding, we propose to identify, extract, and analyze 41 textual and phonemic features that might be more complex to (de)code in French CS. For the automatic extraction of complexity, several tools are used: FABRA for readability, SPPAS for phonetization and CS key generation. The results show some strong correlations between readability features, few between phonemic variables, and few between the two types. An initial model is proposed for selecting texts to be recorded for learning French CS."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="norre-etal-2026-automatic">
<titleInfo>
<title>Automatic Extraction of Textual and Phonemic Complexity for French Cued Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Magali</namePart>
<namePart type="family">Norré</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brigitte</namePart>
<namePart type="family">Bigi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Gala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ludivine</namePart>
<namePart type="given">Javourey</namePart>
<namePart type="family">Drevet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">François</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">François</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Amaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Baptista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Cardon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Stodden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amalia</namePart>
<namePart type="family">Todirascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Wilkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article presents the results of an analysis of a written corpus with the view of automatically generating it in French Cued Speech (CS). CS is a communication system developed for people with hearing impairment to complement speech reading at the phonetic level using hands. This visual communication mode uses handshapes in different positions near the face in combination with the mouthshape (called ‘cues’ or ‘keys’) to make the phonemes of spoken language look different from each other. Despite many studies demonstrating its benefits, there are few resources available for learning and practicing it, especially in French. As part of a wider project aimed at creating an online learning platform with automatically generated videos using an augmented reality system displaying a virtual coding, we propose to identify, extract, and analyze 41 textual and phonemic features that might be more complex to (de)code in French CS. For the automatic extraction of complexity, several tools are used: FABRA for readability, SPPAS for phonetization and CS key generation. The results show some strong correlations between readability features, few between phonemic variables, and few between the two types. An initial model is proposed for selecting texts to be recorded for learning French CS.</abstract>
<identifier type="citekey">norre-etal-2026-automatic</identifier>
<identifier type="doi">10.63317/2efggr7hkgst</identifier>
<location>
<url>https://aclanthology.org/2026.readi-1.5/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>61</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Extraction of Textual and Phonemic Complexity for French Cued Speech
%A Norré, Magali
%A Bigi, Brigitte
%A Gala, Núria
%A Drevet, Ludivine Javourey
%A François, Thomas
%Y Shardlow, Matthew
%Y François, Thomas
%Y Amaro, Raquel
%Y Baptista, Jorge
%Y Cardon, Rémi
%Y Ribeiro, Eugénio
%Y Saggion, Horacio
%Y Stodden, Regina
%Y Todirascu, Amalia
%Y Wilkens, Rodrigo
%S Proceedings of the Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F norre-etal-2026-automatic
%X This article presents the results of an analysis of a written corpus with the view of automatically generating it in French Cued Speech (CS). CS is a communication system developed for people with hearing impairment to complement speech reading at the phonetic level using hands. This visual communication mode uses handshapes in different positions near the face in combination with the mouthshape (called ‘cues’ or ‘keys’) to make the phonemes of spoken language look different from each other. Despite many studies demonstrating its benefits, there are few resources available for learning and practicing it, especially in French. As part of a wider project aimed at creating an online learning platform with automatically generated videos using an augmented reality system displaying a virtual coding, we propose to identify, extract, and analyze 41 textual and phonemic features that might be more complex to (de)code in French CS. For the automatic extraction of complexity, several tools are used: FABRA for readability, SPPAS for phonetization and CS key generation. The results show some strong correlations between readability features, few between phonemic variables, and few between the two types. An initial model is proposed for selecting texts to be recorded for learning French CS.
%R 10.63317/2efggr7hkgst
%U https://aclanthology.org/2026.readi-1.5/
%U https://doi.org/10.63317/2efggr7hkgst
%P 61-73
Markdown (Informal)
[Automatic Extraction of Textual and Phonemic Complexity for French Cued Speech](https://aclanthology.org/2026.readi-1.5/) (Norré et al., READI-TSAR 2026)
ACL