The INTERSPEECH 2017 Computational Paralinguistics Challenge: Addressee, Cold & Snoring
Conference Paper
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.
Full Text
Duke Authors
Cited Authors
- Schuller, B; Steidl, S; Batliner, A; Bergelson, E; Krajewski, J; Janott, C; Amatuni, A; Casillas, M; Seidl, A; Soderstrom, M; Warlaumont, AS; Hidalgo, G; Schnieder, S; Heiser, C; Hohenhorst, W; Herzog, M; Schmitt, M; Qian, K; Zhang, Y; Trigeorgis, G; Tzirakis, P; Zafeiriou, S
Published Date
- January 1, 2017
Published In
Volume / Issue
- 2017-August /
Start / End Page
- 3442 - 3446
Electronic International Standard Serial Number (EISSN)
- 1990-9772
International Standard Serial Number (ISSN)
- 2308-457X
Digital Object Identifier (DOI)
- 10.21437/Interspeech.2017-43
Citation Source
- Scopus