CPSD — Child Pathological Speech Database
Date and place of creation: 2011, Institut des Systèmes Intelligents et de Robotique, Sorbonne Université - former Université Pierre et Marie Curie Paris VI, France
Authors: Fabien Ringeval, Julie Demouy, Gyorgy Szaszák, Mohamed Chetouani, Laurence Robel, Jean Xavier, David Cohen, and Monique Plaza
Summary: The CPSD provides speech data as recorded in two university departments of child and adolescent psychiatry, located in Paris, France; Université Pierre et Marie Curie – Pitié Salpêtrière Hospital and Université René Descartes – Necker Hospital. It contains 2.5 k instances of speech recordings from 99 children aged 6 to 18 years. 35 of these children show Pervasive Development Disorders either of autism spectrum condition (PDD, 10 male, 2 female), specific language impairment such as dysphasia (DYS, 10 male, 3 female) or PDD Non-Otherwise Specified (NOS, 9 male, 1 female) according to the DSM-IV criteria. A monolingual control group consists of 64 further children (TYP, 52 male, 12 female). The French speech includes prompted sentence imitation of 26 sentences representing different modalities (declarative, exclamatory, interrogative, and imperative) and four types of intonations (descending, falling, floating, and rising). In addition, 1 k instances are provided as spontaneous expressions during the story-telling of a pictured book charged with different emotions (induced affect).
License: End User License Agreement (EULA) available to academic researchers and researchers in non-for-profit research organisations - contact: cpsd@isir.upmc.fr.
Presence in challenge
Computational Paralinguistic Challenge (ComPare), INTERSPEECH 2013, ISCA.
Related publications
F. Ringeval, J. Demouy, G. Szaszák, M. Chetouani, L. Robel, J. Xavier, D. Cohen, and M. Plaza. "Automatic Intonation Recognition for the Prosodic Assessment of Language-Impaired Children", in IEEE Transactions on Audio, Speech, and Language Processing, vol. 19, no. 5, pp. 1328-1342, July 2011, IEEE, doi: 10.1109/TASL.2010.2090147.
J. Demouy, M. Plaza, J. Xavier, F. Ringeval, M. Chetouani, D. Périsse, D. Chauvin, S. Viaux, B. Golse, D. Cohen, and L. Robel. "Differential language markers of pathology in Autism, Pervasive Developmental Disorder Not Otherwise Specified and Specific Language Impairment", in Research in Autism Spectrum Disorders, vol. 5, no. 4, pp. 1402-1412, October-December 2011, ELSEVIER, doi: 10.1016/j.rasd.2011.01.026.
F. Ringeval, M. Chetouani, and D. Cohen. "Dynamic modeling of prosody: Application to atypical prosody recognition in ASD, PDD-NOS and specific language impairment", in Neuropsychiatrie de l'Enfance et de l'Adolescence, vol. 60, no. 5, pp.S32, July 2012, ELSEVIER, doi: 10.1016/j.neurenf.2012.05.104.
B. Schuller, S. Steidl, A. Batliner, A. Vinciarelli, K. Scherer, F. Ringeval, M. Chetouani, F. Weninger, F, Eyben, E. Marchi, M. Mortillaro, H. Salamin, A. Polychroniou, F. Valente, and S. Kim. "The INTERSPEECH 2013 Computational Paralinguistics Challenge: Social signals, Conflict, Emotion, Autism", in proceedings of Interspeech 2013, International Speech Communication Association (ISCA), pp. 148-152, 2013, ISCA, doi: 10.21437/Interspeech.2013-56.
M. Schmitt, E. Marchi, F. Ringeval and B. Schuller. "Towards Cross-lingual Automatic Diagnosis of Autism Spectrum Condition in Children's Voices", in proceedings of Speech Communication, 12. ITG Symposium, pp. 400-412, 2016, VDE Verlag, ISBN:978-3-8007-4275-2.
F. Ringeval, E. Marchi, C. Grossard, J. Xavier, M. Chetouani, D. Cohen, and B. Schuller. "Automatic Analysis of Typical and Atypical Encoding of Spontaneous Emotion in the Voice of Children", in proceedings of Interspeech 2016, International Speech Communication Association (ISCA), pp. 1210-1214, 2016, doi: 10.21437/Interspeech.2016-766.
A. Mencattini, F. Mosciano, M.C. Comes, T. Di Gregorio, G. Raguso, E. Daprati, F. Ringeval, B. Schuller, C. Di Natale, and E. Martinelli. "An emotional modulation model as signature for the identification of children developmental disorders", in Nature Scientific Reports vol. 8, article no. 14487, 2018, doi: 10.1038/s41598-018-32454-7.
RECOLA — Remote and Collaborative Affective Interactions Database
Date and place of creation: 2013, Département d'Informatique de l'Université de Fribourg, Université de Fribourg, Switzerland
Authors: Fabien Ringeval, Andreas Sonderreger, Juergen Sauer, Denis Lalanne
Summary: The database consists of audio, visual, and physiological (electrocardiogram, and electrodermal activity) recordings of online dyadic interactions between French speaking participants, who were solving a task in dyadic collaboration. Affective and social behaviours naturally expressed by the participants were reported by themselves, at different steps of the study, and by six French-speaking assistants with continuous dimensions (arousal and intrinsic pleasantness) using a web-based annotation tool, for the first five minutes of interaction. Data from 23 subjects are publicly available. Whereas annotation of participants in the test partition are not publicly available, performance evaluation on this partition can be provided by following the AVEC guidelines. The RECOLA database has been extensively used in the literature to demonstrate the performance of predictive systems and has been used in several challenges.
License: End User License Agreement (EULA) available to both academic and industrial researchers - contact: diuf-recola@unifr.ch
Presence in challenge
Audio Visual Emotion Challenge (AV+EC), ACM MM, 2015
Audio Visual Emotion Challenge (AVEC), ACM MM, 2016
Audio Visual Emotion Challenge (AVEC), ACM MM, 2018
Multi-modal Multiple Appropriate Facial Reaction Generation Challenge (REACT), ACM MM, 2023
Multi-modal Multiple Appropriate Facial Reaction Generation Challenge (REACT), IEEE FG, 2024
Related publications:
F. Ringeval, J. Demouy, G. Szaszák, M. Chetouani, L. Robel, J. Xavier, D. Cohen, and M. Plaza. "Automatic Intonation Recognition for the Prosodic Assessment of Language-Impaired Children", in IEEE Transactions on Audio, Speech, and Language Processing, vol. 19, no. 5, pp. 1328-1342, July 2011, IEEE, doi: 10.1109/TASL.2010.2090147.
SEWA
To be completed...
WhatHeSays
To be completed...
THERADIA WoZ
To be completed...
ANNOT
THERADIA WoZ infer