The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates

Björn W. Schuller; Anton Batliner; Christian Bergler; Cecilia Mascolo; Jing Han; Iulia Lefter; Heysem Kaya; Shahin Amiriparian; Alice Baird; Lukas Stappen; Sandra Ottl; Maurice Gerczuk; Panagiotis Tzirakis; Chloë Brown; Jagmohan Chauhan; Andreas Grammenos; Apinan Hasthanasombat; Dimitris Spathis; Tong Xia; Pietro Cicuta; Leon J.m. Rothkrantz; Joeri A. Zwerts; Jelle Treep; Casper S. Kaandorp

doi:10.21437/interspeech.2021-19

The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates

Björn W. Schuller
, Anton Batliner
, Christian Bergler
, Cecilia Mascolo
, Jing Han
, Iulia Lefter
, Heysem Kaya
, Shahin Amiriparian
, Alice Baird
, Lukas Stappen
, Sandra Ottl
, Maurice Gerczuk
, Panagiotis Tzirakis
, Chloë Brown
, Jagmohan Chauhan
, Andreas Grammenos
, Apinan Hasthanasombat
, Dimitris Spathis
, Tong Xia
, Pietro Cicuta

Leon J.m. Rothkrantz, Joeri A. Zwerts, Jelle Treep, Casper S. Kaandorp

Research output: Contribution to conference › Paper › Academic

Abstract

The INTERSPEECH 2021 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the COVID-19 Cough and COVID-19 Speech Sub-Challenges, a binary classification on COVID-19 infection has to be made based on coughing sounds and speech; in the Escalation Sub- Challenge, a three-way assessment of the level of escalation in a dialogue is featured; and in the Primates Sub-Challenge, four species vs background need to be classified. We describe the Sub-Challenges, baseline feature extraction, and classifiers based on the 'usual' COMPARE and BoAW features as well as deep unsupervised representation learning using the AUDEEP toolkit, and deep feature extraction from pre-trained CNNs using the DEEP SPECTRUM toolkit; in addition, we add deep end-to-end sequential modelling, and partially linguistic analysis.

Original language	English
Pages	431-435
Number of pages	5
DOIs	https://doi.org/10.21437/interspeech.2021-19
Publication status	Published - 30 Aug 2021
Event	INTERSPEECH 2021 - Brno, Czech Republic Duration: 30 Aug 2021 → 3 Sept 2021 https://www.interspeech2021.org/

Conference

Conference	INTERSPEECH 2021
Abbreviated title	INTERSPEECH 2021
Country/Territory	Czech Republic
City	Brno
Period	30/08/21 → 3/09/21
Internet address	https://www.interspeech2021.org/

Bibliographical note

Funding Information:
We acknowledge funding from the DFG’s Reinhart Koselleck project No. 442218748 (AUDI0NOMOUS), the EU’s HORIZON 2020 Grant No. 115902 (RADAR CNS), and the ERC project No. 833296 (EAR).

Publisher Copyright:
Copyright © 2021 ISCA.

Keywords

COVID-19
Challenge
Computational paralinguistics
Escalation
Primates

Access to Document

10.21437/interspeech.2021-19

Cite this

Schuller, B. W., Batliner, A., Bergler, C., Mascolo, C., Han, J., Lefter, I., Kaya, H., Amiriparian, S., Baird, A., Stappen, L., Ottl, S., Gerczuk, M., Tzirakis, P., Brown, C., Chauhan, J., Grammenos, A., Hasthanasombat, A., Spathis, D., Xia, T., ... Kaandorp, C. S. (2021). The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates. 431-435. Paper presented at INTERSPEECH 2021, Brno, Czech Republic. https://doi.org/10.21437/interspeech.2021-19

@conference{67a769fc005f4a8eacbf0af1edee26c6,

title = "The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation \& Primates",

abstract = "The INTERSPEECH 2021 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the COVID-19 Cough and COVID-19 Speech Sub-Challenges, a binary classification on COVID-19 infection has to be made based on coughing sounds and speech; in the Escalation Sub- Challenge, a three-way assessment of the level of escalation in a dialogue is featured; and in the Primates Sub-Challenge, four species vs background need to be classified. We describe the Sub-Challenges, baseline feature extraction, and classifiers based on the 'usual' COMPARE and BoAW features as well as deep unsupervised representation learning using the AUDEEP toolkit, and deep feature extraction from pre-trained CNNs using the DEEP SPECTRUM toolkit; in addition, we add deep end-to-end sequential modelling, and partially linguistic analysis. ",

keywords = "COVID-19, Challenge, Computational paralinguistics, Escalation, Primates",

author = "Schuller, \{Bj{\"o}rn W.\} and Anton Batliner and Christian Bergler and Cecilia Mascolo and Jing Han and Iulia Lefter and Heysem Kaya and Shahin Amiriparian and Alice Baird and Lukas Stappen and Sandra Ottl and Maurice Gerczuk and Panagiotis Tzirakis and Chlo{\"e} Brown and Jagmohan Chauhan and Andreas Grammenos and Apinan Hasthanasombat and Dimitris Spathis and Tong Xia and Pietro Cicuta and Rothkrantz, \{Leon J.m.\} and Zwerts, \{Joeri A.\} and Jelle Treep and Kaandorp, \{Casper S.\}",

note = "Funding Information: We acknowledge funding from the DFG{\textquoteright}s Reinhart Koselleck project No. 442218748 (AUDI0NOMOUS), the EU{\textquoteright}s HORIZON 2020 Grant No. 115902 (RADAR CNS), and the ERC project No. 833296 (EAR). Publisher Copyright: Copyright {\textcopyright} 2021 ISCA.; INTERSPEECH 2021, INTERSPEECH 2021 ; Conference date: 30-08-2021 Through 03-09-2021",

year = "2021",

month = aug,

day = "30",

doi = "10.21437/interspeech.2021-19",

language = "English",

pages = "431--435",

url = "https://www.interspeech2021.org/",

}

Schuller, BW, Batliner, A, Bergler, C, Mascolo, C, Han, J, Lefter, I, Kaya, H, Amiriparian, S, Baird, A, Stappen, L, Ottl, S, Gerczuk, M, Tzirakis, P, Brown, C, Chauhan, J, Grammenos, A, Hasthanasombat, A, Spathis, D, Xia, T, Cicuta, P, Rothkrantz, LJM, Zwerts, JA , Treep, J & Kaandorp, CS 2021, 'The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates', Paper presented at INTERSPEECH 2021, Brno, Czech Republic, 30/08/21 - 3/09/21 pp. 431-435. https://doi.org/10.21437/interspeech.2021-19

TY - CONF

T1 - The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates

AU - Schuller, Björn W.

AU - Batliner, Anton

AU - Bergler, Christian

AU - Mascolo, Cecilia

AU - Han, Jing

AU - Lefter, Iulia

AU - Kaya, Heysem

AU - Amiriparian, Shahin

AU - Baird, Alice

AU - Stappen, Lukas

AU - Ottl, Sandra

AU - Gerczuk, Maurice

AU - Tzirakis, Panagiotis

AU - Brown, Chloë

AU - Chauhan, Jagmohan

AU - Grammenos, Andreas

AU - Hasthanasombat, Apinan

AU - Spathis, Dimitris

AU - Xia, Tong

AU - Cicuta, Pietro

AU - Rothkrantz, Leon J.m.

AU - Zwerts, Joeri A.

AU - Treep, Jelle

AU - Kaandorp, Casper S.

N1 - Funding Information: We acknowledge funding from the DFG’s Reinhart Koselleck project No. 442218748 (AUDI0NOMOUS), the EU’s HORIZON 2020 Grant No. 115902 (RADAR CNS), and the ERC project No. 833296 (EAR). Publisher Copyright: Copyright © 2021 ISCA.

PY - 2021/8/30

Y1 - 2021/8/30

N2 - The INTERSPEECH 2021 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the COVID-19 Cough and COVID-19 Speech Sub-Challenges, a binary classification on COVID-19 infection has to be made based on coughing sounds and speech; in the Escalation Sub- Challenge, a three-way assessment of the level of escalation in a dialogue is featured; and in the Primates Sub-Challenge, four species vs background need to be classified. We describe the Sub-Challenges, baseline feature extraction, and classifiers based on the 'usual' COMPARE and BoAW features as well as deep unsupervised representation learning using the AUDEEP toolkit, and deep feature extraction from pre-trained CNNs using the DEEP SPECTRUM toolkit; in addition, we add deep end-to-end sequential modelling, and partially linguistic analysis.

AB - The INTERSPEECH 2021 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the COVID-19 Cough and COVID-19 Speech Sub-Challenges, a binary classification on COVID-19 infection has to be made based on coughing sounds and speech; in the Escalation Sub- Challenge, a three-way assessment of the level of escalation in a dialogue is featured; and in the Primates Sub-Challenge, four species vs background need to be classified. We describe the Sub-Challenges, baseline feature extraction, and classifiers based on the 'usual' COMPARE and BoAW features as well as deep unsupervised representation learning using the AUDEEP toolkit, and deep feature extraction from pre-trained CNNs using the DEEP SPECTRUM toolkit; in addition, we add deep end-to-end sequential modelling, and partially linguistic analysis.

KW - COVID-19

KW - Challenge

KW - Computational paralinguistics

KW - Escalation

KW - Primates

UR - https://www.scopus.com/pages/publications/85117583478

U2 - 10.21437/interspeech.2021-19

DO - 10.21437/interspeech.2021-19

M3 - Paper

SP - 431

EP - 435

T2 - INTERSPEECH 2021

Y2 - 30 August 2021 through 3 September 2021

ER -

The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this