TY - GEN
T1 - The acm multimedia 2022 computational paralinguistics challenge
T2 - 30th ACM International Conference on Multimedia, MM 2022
AU - Schuller, Bjorn
AU - Batliner, Anton
AU - Amiriparian, Shahin
AU - Bergler, Christian
AU - Gerczuk, Maurice
AU - Holz, Natalie
AU - Larrouy-Maestri, Pauline
AU - Bayerl, Sebastien
AU - Riedhammer, Korbinian
AU - Mallol-Ragolta, Adria
AU - Pateraki, Maria
AU - Coppock, Harry
AU - Kiskin, Ivan
AU - Sinka, Marianne
AU - Roberts, Stephen
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/10/10
Y1 - 2022/10/10
N2 - The ACM Multimedia 2022 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the Vocalisations and Stuttering Sub-Challenges, a classification on human non-verbal vocalisations and speech has to be made; the Activity Sub-Challenge aims at beyond-audio human activity recognition from smartwatch sensor data; and in the Mosquitoes Sub-Challenge, mosquitoes need to be detected. We describe the Sub-Challenges, baseline feature extraction, and classifiers based on the 'usual' ComParE and BoAW features, the auDeep toolkit, and deep feature extraction from pre-trained CNNs using the DeepSpectrum toolkit; in addition, we add end-to-end sequential modelling, and a log-mel-128-BNN.
AB - The ACM Multimedia 2022 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the Vocalisations and Stuttering Sub-Challenges, a classification on human non-verbal vocalisations and speech has to be made; the Activity Sub-Challenge aims at beyond-audio human activity recognition from smartwatch sensor data; and in the Mosquitoes Sub-Challenge, mosquitoes need to be detected. We describe the Sub-Challenges, baseline feature extraction, and classifiers based on the 'usual' ComParE and BoAW features, the auDeep toolkit, and deep feature extraction from pre-trained CNNs using the DeepSpectrum toolkit; in addition, we add end-to-end sequential modelling, and a log-mel-128-BNN.
KW - benchmark
KW - challenge
KW - computational paralinguistics
KW - human activity recognition
KW - mosquito detection
KW - stuttering
KW - vocalisations
UR - http://www.scopus.com/inward/record.url?scp=85151155790&partnerID=8YFLogxK
U2 - 10.1145/3503161.3551591
DO - 10.1145/3503161.3551591
M3 - Conference contribution
AN - SCOPUS:85151155790
T3 - MM 2022 - Proceedings of the 30th ACM International Conference on Multimedia
SP - 7120
EP - 7124
BT - MM 2022 - Proceedings of the 30th ACM International Conference on Multimedia
PB - Association for Computing Machinery, Inc
Y2 - 10 October 2022 through 14 October 2022
ER -