Optimizing linguistic materials for feature-based intelligibility assessment in speech impairments - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Behavior Research Methods Année : 2022

Optimizing linguistic materials for feature-based intelligibility assessment in speech impairments

Anna K Marczyk
  • Fonction : Auteur
  • PersonId : 1041539
Alain Ghio
Muriel Lalain
Marie Rebourg
Corinne Fredouille

Résumé

Assessing the intelligibility of speech-disordered individuals generally involves asking them to read aloud texts such as word lists, a procedure that can be time-consuming if the materials are lengthy. This paper seeks to optimize such elicitation materials by identifying an optimal trade-off between the quantity of material needed for assessment purposes and its capacity to elicit a robust intelligibility metrics. More specifically, it investigates the effect of reducing the number of pseudowords used in a phonetic-acoustic decoding task in a speech-impaired population in terms of the subsequent impact on the intelligibility classifier as quantified by accuracy indexes (AUC of ROC, Balanced Accuracy index and F-scores). A comparison of obtained accuracy indexes shows that when reduction of the amount of elicitation material is based on a phonetic criterion—here, related to phonotactic complexity—the classifier has a higher classifying ability than when the material is arbitrarily reduced. Crucially, downsizing the material to about 30%of the original dataset does not diminish the classifier’s performance nor affect its stability. This result is of significant interest to clinicians as well as patients since it validates a tool that is both reliable and efficient.

Dates et versions

hal-03325628 , version 1 (25-08-2021)

Identifiants

Citer

Anna K Marczyk, Alain Ghio, Muriel Lalain, Marie Rebourg, Corinne Fredouille, et al.. Optimizing linguistic materials for feature-based intelligibility assessment in speech impairments. Behavior Research Methods, 2022, 54 (1), pp.42-53. ⟨10.3758/s13428-021-01610-9⟩. ⟨hal-03325628⟩
56 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More