Publication result detail

BESST Dataset: A Multimodal Resource for Speech-based Stress Detection and Analysis

PEŠÁN, J.; JUŘÍK, V.; KARAFIÁT, M.; ČERNOCKÝ, J.

Original Title

BESST Dataset: A Multimodal Resource for Speech-based Stress Detection and Analysis

English Title

BESST Dataset: A Multimodal Resource for Speech-based Stress Detection and Analysis

Type

Paper in proceedings (conference paper)

Original Abstract

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 investigations into the interplay between stress and speech. In this paper, we introduce the BESST dataset and provide a details of its design, collection protocols, and technical aspects. The dataset comprises speech samples, physiologi- cal 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 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 for research and development.

English abstract

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 investigations into the interplay between stress and speech. In this paper, we introduce the BESST dataset and provide a details of its design, collection protocols, and technical aspects. The dataset comprises speech samples, physiologi- cal 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 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 for research and development.

Keywords

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

Key words in English

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

Authors

PEŠÁN, J.; JUŘÍK, V.; KARAFIÁT, M.; ČERNOCKÝ, J.

RIV year

2025

Released

01.09.2024

Publisher

International Speech Communication Association

Location

Kos

Book

Proceedings of Interspeech 2024

ISBN

1990-9772

Periodical

Proceedings of Interspeech

Volume

2024

Number

9

State

French Republic

Pages from

1355

Pages to

1359

Pages count

5

URL

https://www.isca-archive.org/interspeech_2024/pesan24_interspeech.pdf

BibTex

@inproceedings{BUT193740,
  author="PEŠÁN, J. and JUŘÍK, V. and KARAFIÁT, M. and ČERNOCKÝ, J.",
  title="BESST Dataset: A Multimodal Resource for Speech-based Stress Detection and Analysis",
  booktitle="Proceedings of Interspeech 2024",
  year="2024",
  journal="Proceedings of Interspeech",
  volume="2024",
  number="9",
  pages="1355--1359",
  publisher="International Speech Communication Association",
  address="Kos",
  doi="10.21437/Interspeech.2024-42",
  issn="1990-9772",
  url="https://www.isca-archive.org/interspeech_2024/pesan24_interspeech.pdf"
}

Documents

pesan_2024_interspeech