TY - JOUR
T1 - The INTERSPEECH 2017 Computational Paralinguistics Challenge
T2 - 18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017
AU - Schuller, Björn
AU - Steidl, Stefan
AU - Batliner, Anton
AU - Bergelson, Elika
AU - Krajewski, Jarek
AU - Janott, Christoph
AU - Amatuni, Andrei
AU - Casillas, Marisa
AU - Seidl, Amanda
AU - Soderstrom, Melanie
AU - Warlaumont, Anne S.
AU - Hidalgo, Guillermo
AU - Schnieder, Sebastian
AU - Heiser, Clemens
AU - Hohenhorst, Winfried
AU - Herzog, Michael
AU - Schmitt, Maximilian
AU - Qian, Kun
AU - Zhang, Yue
AU - Trigeorgis, George
AU - Tzirakis, Panagiotis
AU - Zafeiriou, Stefanos
N1 - Publisher Copyright:
Copyright © 2017 ISCA.
PY - 2017
Y1 - 2017
N2 - The INTERSPEECH 2017 Computational Paralinguistics Challenge addresses three different problems for the first time in research competition under well-defined conditions: In the Addressee sub-challenge, it has to be determined whether speech produced by an adult is directed towards another adult or towards a child; in the Cold sub-challenge, speech under cold has to be told apart from 'healthy' speech; and in the Snoring sub-challenge, four different types of snoring have to be classified. In this paper, we describe these sub-challenges, their conditions, and the baseline feature extraction and classifiers, which include data-learnt feature representations by end-to-end learning with convolutional and recurrent neural networks, and bag-of-audio-words for the first time in the challenge series.
AB - The INTERSPEECH 2017 Computational Paralinguistics Challenge addresses three different problems for the first time in research competition under well-defined conditions: In the Addressee sub-challenge, it has to be determined whether speech produced by an adult is directed towards another adult or towards a child; in the Cold sub-challenge, speech under cold has to be told apart from 'healthy' speech; and in the Snoring sub-challenge, four different types of snoring have to be classified. In this paper, we describe these sub-challenges, their conditions, and the baseline feature extraction and classifiers, which include data-learnt feature representations by end-to-end learning with convolutional and recurrent neural networks, and bag-of-audio-words for the first time in the challenge series.
KW - Addressee
KW - Challenge
KW - Child directed speech
KW - Computational paralinguistics
KW - Snoring
KW - Speech under cold
UR - http://www.scopus.com/inward/record.url?scp=85034265448&partnerID=8YFLogxK
U2 - 10.21437/Interspeech.2017-43
DO - 10.21437/Interspeech.2017-43
M3 - Conference article
AN - SCOPUS:85034265448
SN - 2308-457X
VL - 2017-August
SP - 3442
EP - 3446
JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Y2 - 20 August 2017 through 24 August 2017
ER -