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

J 2024

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

PEŠÁN, Jan; Vojtěch JUŘÍK; Alexandra RUŽIČKOVÁ; Vojtěch SVOBODA; Oto JANOUŠEK et. al.

Basic information

Original name

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

Authors

Edition

Scientific Data, London, Springer Nature, 2024, 2052-4463

Other information

Language

English

Type of outcome

Article in a journal

Field of Study

50101 Psychology

Country of publisher

United Kingdom of Great Britain and Northern Ireland

Confidentiality degree

is not subject to a state or trade secret

References:

URL

Impact factor

Impact factor: 6.900

RIV identification code

RIV/00216224:14210/24:00137626

Organization unit

Faculty of Arts

DOI

https://doi.org/10.1038/s41597-024-03991-w

UT WoS

001353330000007

EID Scopus

2-s2.0-85209350842

Keywords in English

Speech production; stress; machine learning; dataset

Abstract

In the original language

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.

Links

MUNI/A/1519/2023, interní kód MU

Name: Možnosti aplikačního využití poznatků základního psychologického výzkumu

Investor: Masaryk University

Cite

PEŠÁN, Jan; Vojtěch JUŘÍK; Alexandra RUŽIČKOVÁ; Vojtěch SVOBODA; Oto JANOUŠEK; Andrea NĚMCOVÁ; Hana BOJANOVSKÁ; Jasmína ALDABAGHOVÁ; Filip KYSLÍK; Kateřina VODIČKOVÁ; Adéla SODOMOVÁ; Patrik BARTYS; Peter CHUDÝ and Jan ČERNOCKÝ. Speech production under stress for machine learning : multimodal dataset of 79 cases and 8 signals. Scientific Data. London: Springer Nature, 2024, vol. 11, November 2024, p. 1-9. ISSN 2052-4463. Available from: https://doi.org/10.1038/s41597-024-03991-w.

@article{2451484,
   author = {Pešán, Jan and Juřík, Vojtěch and Ružičková, Alexandra and Svoboda, Vojtěch and Janoušek, Oto and Němcová, Andrea and Bojanovská, Hana and Aldabaghová, Jasmína and Kyslík, Filip and Vodičková, Kateřina and Sodomová, Adéla and Bartys, Patrik and Chudý, Peter and Černocký, Jan},
   article_location = {London},
   article_number = {November 2024},
   doi = {https://doi.org/10.1038/s41597-024-03991-w},
   keywords = {Speech production; stress; machine learning; dataset},
   language = {eng},
   issn = {2052-4463},
   journal = {Scientific Data},
   title = {Speech production under stress for machine learning : multimodal dataset of 79 cases and 8 signals},
   url = {https://www.nature.com/articles/s41597-024-03991-w#Abs1},
   volume = {11},
   year = {2024}
}

TY  - JOUR
ID  - 2451484
AU  - Pešán, Jan - Juřík, Vojtěch - Ružičková, Alexandra - Svoboda, Vojtěch - Janoušek, Oto - Němcová, Andrea - Bojanovská, Hana - Aldabaghová, Jasmína - Kyslík, Filip - Vodičková, Kateřina - Sodomová, Adéla - Bartys, Patrik - Chudý, Peter - Černocký, Jan
PY  - 2024
TI  - Speech production under stress for machine learning : multimodal dataset of 79 cases and 8 signals
JF  - Scientific Data
VL  - 11
IS  - November 2024
SP  - 1-9
EP  - 1-9
PB  - Springer Nature
SN  - 20524463
KW  - Speech production
KW  - stress
KW  - machine learning
KW  - dataset
UR  - https://www.nature.com/articles/s41597-024-03991-w#Abs1
N2  - 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.
ER  -

PEŠÁN, Jan; Vojtěch JUŘÍK; Alexandra RUŽIČKOVÁ; Vojtěch SVOBODA; Oto JANOUŠEK; Andrea NĚMCOVÁ; Hana BOJANOVSKÁ; Jasmína ALDABAGHOVÁ; Filip KYSLÍK; Kateřina VODIČKOVÁ; Adéla SODOMOVÁ; Patrik BARTYS; Peter CHUDÝ and Jan ČERNOCKÝ. Speech production under stress for machine learning : multimodal dataset of 79 cases and 8 signals. \textit{Scientific Data}. London: Springer Nature, 2024, vol.~11, November 2024, p.~1-9. ISSN~2052-4463. Available from: https://doi.org/10.1038/s41597-024-03991-w.

Přehled o publikaci