Summary of the paper
| Title | CINEMO ― A French Spoken Language Resource for Complex Emotions: Facts and Baselines |
|---|---|
| Authors | Björn Schuller, Riccardo Zaccarelli, Nicolas Rollet and Laurence Devillers |
| Abstract | The CINEMO corpus of French emotional speech provides a richly annotatedresource to help overcome the apparent lack of learning and testing speechmaterial for complex, i.e. blended or mixed emotions. The protocol for itscollection was dubbing selected emotional scenes from French movies. 51speakers are contained and the total speech time amounts to 2 hours and 13minutes and 4k speech chunks after segmentation. Extensive labelling wascarried out in 16 categories for major and minor emotions and in 6 continuousdimensions. In this contribution we give insight into the corpus statisticsfocusing in particular on the topic of complex emotions, and provide benchmarkrecognition results obtained in exemplary large feature space evaluations. Inthe result the labelling oft he collected speech clearly demonstrates that acomplex handling of emotion seems needed. Further, the automatic recognitionexperiments provide evidence that the automatic recognition of blended emotionsappears to be feasible. |
| Language | Speech resource/database |
| Topics | Corpus (creation, annotation, etc.), Emotion Recognition/Generation, Speech resource/database |
Full paper  |
CINEMO ― A French Spoken Language Resource for Complex Emotions: Facts and Baselines |
| Bibtex | @InProceedings{SCHULLER10.483, author = {Björn Schuller, Riccardo Zaccarelli, Nicolas Rollet and Laurence Devillers}, title = {CINEMO ― A French Spoken Language Resource for Complex Emotions: Facts and Baselines}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |