Speech production under stress for machine learning: multimodal dataset of 79 cases and 8 signals.

Autor: Pešán J; Speech@FIT, Faculty of Information Technology, Brno University of Technology, Brno, Czech Republic., Juřík V; Department of Psychology, Faculty of Arts, Masaryk University, Brno, Czech Republic. jurik.vojtech@mail.muni.cz.; Institute of Computer Aided Engineering and Computer Science, Faculty of Civil Engineering, Brno University of Technology, Brno, Czech Republic. jurik.vojtech@mail.muni.cz., Ružičková A; Department of Psychology, Faculty of Arts, Masaryk University, Brno, Czech Republic., Svoboda V; Department of Psychology, Faculty of Arts, Masaryk University, Brno, Czech Republic., Janoušek O; Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic., Němcová A; Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic., Bojanovská H; Department of Psychology, Faculty of Arts, Masaryk University, Brno, Czech Republic., Aldabaghová J; Department of Psychology, Faculty of Arts, Masaryk University, Brno, Czech Republic., Kyslík F; Department of Psychology, Faculty of Arts, Masaryk University, Brno, Czech Republic., Vodičková K; Department of Psychology, Faculty of Arts, Masaryk University, Brno, Czech Republic., Sodomová A; Department of Psychology, Faculty of Arts, Masaryk University, Brno, Czech Republic., Bartys P; Department of Psychology, Faculty of Arts, Masaryk University, Brno, Czech Republic., Chudý P; Speech@FIT, Faculty of Information Technology, Brno University of Technology, Brno, Czech Republic.; Institute of Computer Science, University of Würzburg, Würzburg, Germany., Černocký J; Speech@FIT, Faculty of Information Technology, Brno University of Technology, Brno, Czech Republic.
Jazyk: angličtina
Zdroj: Scientific data [Sci Data] 2024 Nov 12; Vol. 11 (1), pp. 1221. Date of Electronic Publication: 2024 Nov 12.
DOI: 10.1038/s41597-024-03991-w
Abstrakt: Early identification of cognitive or physical overload is critical in fields where human decision making matters when preventing threats to safety and property. Pilots, drivers, surgeons, and operators of nuclear plants are among those affected by this challenge, as acute stress can impair their cognition. In this context, the significance of paralinguistic automatic speech processing increases for early stress detection. The intensity, intonation, and cadence of an utterance are examples of paralinguistic traits that determine the meaning of a sentence and are often lost in the verbatim transcript. To address this issue, tools are being developed to recognize paralinguistic traits effectively. However, a data bottleneck still exists in the training of paralinguistic speech traits, and the lack of high-quality reference data for the training of artificial systems persists. Regarding this, we present an original empirical dataset collected using the BESST experimental protocol for capturing speech signals under induced stress. With this data, our aim is to promote the development of pre-emptive intervention systems based on stress estimation from speech.
Competing Interests: Competing interests The authors declare no competing interests.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: