Product Details

BESST: Brno Extended Stress and Speech Database

Created: 2024

Czech title
BESST: Brněnská rozšířená stresová a řečová databáze
Type
testing
License
In order to use the result by another entity, it is always necessary to acquire a license
License Fee
The licensor does not require a license fee for the result in some cases
Authors
Pešán Jan, Ing. (DCGM)
Juřík Vojtěch, Mgr., Ph.D. (VUT)
RŮŽIČKOVÁ, A.
SVOBODA, V.
Janoušek Oto, Ing., Ph.D. (UBMI)
Němcová Andrea, Ing., Ph.D. (UBMI)
BOJANOVSKÁ, H.
ALDABAGHOVÁ, J.
KYSLÍK, F.
VODIČKOVÁ, K.
SODOMOVÁ, A.
BARTYS, P.
Chudý Peter, doc. Ing., Ph.D., MBA (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
Keywords

stress recognition, multimodal data, speech research, physiological signals, cognitive load, speech production

Description

The Brno Extended Stress and Speech Test (BESST) dataset is a new resource for the speech research community, offering multimodal audiovisual, physiological and psychological data that enable comprehensive investigations into the interplay between stress and speech. In this product, we introduce the BESST dataset and provide a detailed overview of its design, data collection protocols, and technical aspects. The dataset comprises speech samples, physiological signals (including electrocardiogram, electrodermal activity, skin temperature, and acceleration data), and video recordings from 90 subjects performing stress-inducing tasks. It comprises 16.9 hours of clean Czech speech data, averaging 15 minutes of clean speech per participant. The data collection procedure involves the induction of both cognitive and physical stress induced by Reading Span task (RSPAN) and Hand Immersion (HIT) task respectively. The BESST dataset was collected under stringent ethical standards and is accessible under permissive license for research and development.

Location
License Conditions

For information on the license conditions, please contact the transfer manager at FIT BUT. Considering the nature of the data, the condition for granting a license to interested parties is the simultaneous conclusion of an obligation to comply with the terms of personal data processing.

Research groups
Departments
Back to top