Publication Details
Speech production under stress for machine learning: multimodal dataset of 79 cases and 8 signals
Juřík Vojtěch, Mgr., Ph.D. (VUT)
Růžičková Alexandra
Svoboda Vojtěch, Bc.
Janoušek Oto, Ing., Ph.D. (UBMI)
Němcová Andrea, Ing., Ph.D. (UBMI)
Bojanovská Hana, Bc.
Aldabaghová Jasmína, Mgr.
Kyslík Filip
Vodičková Kateřina, Bc.
Sodomová Adéla, Bc.
Bartys Patrik, Mgr.
Chudý Peter, doc. Ing., Ph.D., MBA (FIT)
Černocký Jan, prof. Dr. Ing. (DCGM)
speech, stress, machine learning
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.
@article{BUT193434,
author="Jan {Pešán} and Vojtěch {Juřík} and Alexandra {Růžičková} and Vojtěch {Svoboda} and Oto {Janoušek} and Andrea {Němcová} and Hana {Bojanovská} and Jasmína {Aldabaghová} and Filip {Kyslík} and Kateřina {Vodičková} and Adéla {Sodomová} and Patrik {Bartys} and Peter {Chudý} and Jan {Černocký}",
title="Speech production under stress for machine learning: multimodal dataset of 79 cases and 8 signals",
journal="Scientific data",
year="2024",
volume="11",
number="1",
pages="1--9",
doi="10.1038/s41597-024-03991-w",
issn="2052-4463",
url="https://www.nature.com/articles/s41597-024-03991-w"
}