The INTERSPEECH 2010 paralinguistic challenge

By Björn Schuller, Stefan Steidl, Anton Batliner, Felix Burkhardt, Laurence Y. Devillers, Christian A. Müller, Shrikanth S. Narayanan. Interspeech, 2010

597 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/328d0ad8a45ad58cd1d63d6ff296aec387890b6f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Emotion representation, analysis and synthesis in continuous space: A survey (2011, background): “Another pioneering attempt is that of INTERSPEECH 2010 Paralinguistic Challenge featuring the Affect Sub-challenge with a focus on dimensional affect [60].”
Categorical and dimensional affect analysis in continuous input: Current trends and future directions (2013, unknown): “In order to bring together and test the existing efforts for automatic affect analysis, a pioneering attempt has been that of the INTERSPEECH 2009 Emotion Challenge [190] and the INTERSPEECH2010Paralinguistic Challenge featuring the Affect Sub-challenge [191].”
AVEC 2011-The First International Audio/Visual Emotion Challenge (2011, methodology): “In this Challenge, an extended set of features with respect to the INTERSPEECH 2009 Emotion Challenge (384 features) [13] and INTERSPEECH 2010 Paralinguistic Challenge (1 582 features) [14] is given to the participants, again using the freely available open-source Emotion and Affect Recognition (ope”
Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge (2011, methodology): “An interesting aspect of the openEAR toolkit is that it provides pre-deﬁned sets of derived functionals for comparison such as the sets provided for the INTERSPEECH 2009 Emotion Challenge (Schuller et al., 2009d) and the following INTERSPEECH 2010 Paralinguistic Challenge (Schuller et al., 2010c).”
AVEC 2014: 3D Dimensional Affect and Depression Recognition Challenge (2014, methodology): “extended set of features with respect to the INTERSPEECH 2009 Emotion Challenge (384 features) [24] and INTERSPEECH 2010 Paralinguistic Challenge (1 582 features) [25] is given to the participants, again using the freely available open-source Emotion and Affect Recognition (openEAR) [8] toolkit’s fe”
AVEC 2013: the continuous audio/visual emotion and depression recognition challenge (2013, methodology): “2011, an extended set of features with respect to the INTERSPEECH 2009 Emotion Challenge (384 features) [22] and INTERSPEECH 2010 Paralinguistic Challenge (1 582 features) [23] is given to the participants, again using the freely available open-source Emotion and Affect Recognition (openEAR) [7] too”
Video and Image based Emotion Recognition Challenges in the Wild: EmotiW 2015 (2015, methodology): “The parameters are: range = [0-360], pyramid levels = 3 and number of bins = 16.”
Learning Affective Features With a Hybrid Deep Model for Audio–Visual Emotion Recognition (2018, methodology): “As suggested in [60], we adopt the subject-independent Leave-One-Subject-Out (LOSO) and Leave-One-Speakers-Group-Out (LOSGO) cross-validation strategies for experiments, which are commonly used in real-world applications.”
Multimodal Continuous Emotion Recognition with Data Augmentation Using Recurrent Neural Networks (2018, methodology): “Specifically, we extract the baseline audio feature set of INTERSPEECH 2010 Paralinguistic Challenge (IS10) [40] which can better reflect a border coverage of paralinguistic information assessment.”
Computational Sociolinguistics: A Survey (2016, background): “er and they represent a rich source for the study of social behavior. Among the so-called paralinguistic aspects for which detection models and evaluation frameworks exist are age, gender and affect (Schuller et al. 2010). The increasing volumes of recordings of spoken dialogue and aligned transcrip”
Evaluating deep learning architectures for Speech Emotion Recognition (2017, background): “Whether performing turn-based processing or frame-based processing, most of the research effort in the last decade has been devoted to selecting an optimal set of features (Schuller et al., 2010).”
AVEC 2012: the continuous audio/visual emotion challenge (2012, background): “2009 Emotion Challenge (384 features) [14] and INTERSPEECH 2010 Paralinguistic Challenge (1 582 features) [15]”
The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing (2016, methodology): “The proposed minimal sets are compared to five large-scale, brute-forced baseline acoustic feature sets of the INTERSPEECH 2009 Emotion Challenge [43] (384 parameters), the INTERSPEECH 2010 Paralinguistic Challenge [36] (1,582 parameters), the INTERSPEECH 2011 Speaker State Challenge [44] (4,368 par”