How to Design a Relevant Corpus for Sleepiness Detection Through Voice?

Martin, Vincent; Rouas, Jean-Luc; Micoulaud‐Franchi, Jean‐Arthur; Philip, Pierre; Krajewski, Jarek

doi:10.3389/fdgth.2021.686068

Cited by 13 publications

(12 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…On the other side, the available finesse both in terms of time and concept for ML algorithms are restricted to (static) datasets, chosen by the dataset designer ( 41 ).…”

Section: Discussionmentioning

confidence: 99%

How Does Comparison With Artificial Intelligence Shed Light on the Way Clinicians Reason? A Cross-Talk Perspective

et al. 2022

View full text Add to dashboard Cite

In order to create a dynamic for the psychiatry of the future, bringing together digital technology and clinical practice, we propose in this paper a cross-teaching translational roadmap comparing clinical reasoning with computational reasoning. Based on the relevant literature on clinical ways of thinking, we differentiate the process of clinical judgment into four main stages: collection of variables, theoretical background, construction of the model, and use of the model. We detail, for each step, parallels between: i) clinical reasoning; ii) the ML engineer methodology to build a ML model; iii) and the ML model itself. Such analysis supports the understanding of the empirical practice of each of the disciplines (psychiatry and ML engineering). Thus, ML does not only bring methods to the clinician, but also supports educational issues for clinical practice. Psychiatry can rely on developments in ML reasoning to shed light on its own practice in a clever way. In return, this analysis highlights the importance of subjectivity of the ML engineers and their methodologies.

show abstract

“…On the other side, the available finesse both in terms of time and concept for ML algorithms are restricted to (static) datasets, chosen by the dataset designer ( 41 ).…”

Section: Discussionmentioning

confidence: 99%

How Does Comparison With Artificial Intelligence Shed Light on the Way Clinicians Reason? A Cross-Talk Perspective

et al. 2022

View full text Add to dashboard Cite

show abstract

“…g . participant identity and sleep deprivation observed in previous databases (25, 32). Second, we use a fully generic acoustic feature set, derived from an established model of auditory processing (33).…”

Section: Introductionmentioning

confidence: 92%

Sleep deprivation detected by voice analysis

Thoret

Andrillon

Gauriau

et al. 2022

Preprint

View full text Add to dashboard Cite

Using our voice represent an exquisitely intricate act, recruiting a host of cognitive and motor functions. As such, the voice is bound to reflect many aspects of the internal state of the speaker: personality, infections, stress, emotions. Here, we investigate whether sleep deprivation in otherwise normal and healthy persons can be detected through machine-learning analysis of vocal recordings. In contrast to previous approaches, we use fully generic acoustic features, derived from auditory-inspired models of sound processing, together with recently-developed machine learning interpretation techniques. Our results show that sleep deprivation can be accurately detected from generic acoustic features of vocal recordings. Two main different types of features were impacted by sleep deprivation: one related to speech rhythms, the other related to the timbre of the voice. We speculate that these features reflect two distinct physiological processes: the cognitive control of speech production and an inflammatory effect of the vocal apparatus. Crucially, the relative balance of these two effects varied widely for each individual, suggesting that the voice may be used as a "sleep stethoscope" to better understand the variety of idiosyncratic responses to sleep deprivation. Moreover, the method we outline is fully general and could be applied to the future investigation of any type of vocal biomarkers using machine-learning techniques.

show abstract

“…Les caractéristiques traits des sujets, déterminé génétiquement, peuvent aussi interférer avec la mesure de l'hypersomnolence et seront à prendre en compte, avec en particulier le chronotype (différences individuelles dans la phase, c'est-à-dire moment de sommeil ou d'éveil, du matin ou du soir), le somnotype (propension à un besoin de quantité de sommeil, de courte à longue) (143) ou encore le trototype (sensibilité aux répercussions d'un sommeil de qualité ou de quantité diminuée sur les performances). À partir de précédents travaux que nous avons réalisés (144), sur la base du modèle de Lopez et coll., de précédentes revues sur la fatigue et la vigilance (2,12), et de définitions proposées au sein de l'initiative Research domain criteria (RDoC) (145), nous proposons dans la Figure 2 un modèle relationnel des construits liés à la somnolence et à l'hypersomnolence et de leurs outils de mesure les plus utilisés, à la fois sur le plan clinique (partie inférieure de la figure) et psychophysiologique (partie supérieure de la figure). Ce modèle préliminaire qui reste à confirmer et à ajuster permet de replacer les outils d'évaluation de la somnolence et de l'hypersomnolence dans un contexte plus large, en lien avec les mécanismes physiopathologiques, cérébraux, cognitifs sous-jacents qu'il reste à mieux identifier par les outils des neurosciences intégratives du sommeil.…”

Section: Pour Une Médecine De Précision De L'hypersomnolenceunclassified