Using reading mistakes as features for sleepiness detection in speech - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Using reading mistakes as features for sleepiness detection in speech

Résumé

Automatic detection of sleepiness can help to improve the follow-up of patients suffering from chronic diseases. Previous research on sleepiness detection has shown that this task is feasible using voice recordings. Most studies however rely on numerous features extracted from healthy subjects recordings and machine learning, the target being the output of subjective sleepiness questionnaires. In this paper, we propose to study the reading errors made by patients suffering from Excessive Daytime Sleepiness on the reading tasks of the Objective and Subjective Sleepiness Voice Corpus collected at the Bordeaux hospital. This database differs from the others on two key points: patients are recorded instead of healthy subjects and their sleepiness level is assessed using multiple measurements, both subjective and objective. With the help of Speech Therapists, we defined and counted reading errors and confront these numbers with sleepiness measurements. We show that evaluating these reading errors can be useful to elaborate robust markers of objective sleepiness but also to elaborate exclusion criteria of the speakers not having a sufficient reading level.
Fichier principal
Vignette du fichier
Speech_Prosody_2020_final_version_.pdf (183.14 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02495149 , version 1 (18-03-2020)
hal-02495149 , version 2 (12-04-2020)

Identifiants

  • HAL Id : hal-02495149 , version 2

Citer

Vincent P. Martin, Gabrielle Chapouthier, Mathilde Rieant, Jean-Luc Rouas, Pierre Philip. Using reading mistakes as features for sleepiness detection in speech. 10th International Conference on Speech Prosody 2020, May 2020, Tokyo, Japan. pp.985-989. ⟨hal-02495149v2⟩

Collections

CNRS
116 Consultations
141 Téléchargements

Partager

Gmail Facebook X LinkedIn More