Automatic Segmentation of Spontaneous Data using Dimensional Labels from Multiple Coders

Share/Save/Bookmark

Nicolaou, Mihalis A. and Gunes, Hatice and Pantic, Maja (2010) Automatic Segmentation of Spontaneous Data using Dimensional Labels from Multiple Coders. In: Multimodal Corpora: Advances in Capturing, Coding and Analyzing Multimodality, 18 May 2010, Valletta, Malta (pp. pp. 43-48).

open access
[img]
Preview
PDF
579kB
Abstract:This paper focuses on automatic segmentation of spontaneous data using continuous dimensional labels from multiple coders. It introduces efficient algorithms to the aim of (i) producing ground-truth by maximizing inter-coder agreement, (ii) eliciting the frames or samples that capture the transition to and from an emotional state, and (iii) automatic segmentation of spontaneous audio-visual data to be used by machine learning techniques that cannot handle unsegmented sequences. As a proof of concept, the algorithms introduced are tested using data annotated in arousal and valence space. However, they can be straightforwardly applied to data annotated in other continuous emotional spaces, such as power and expectation.
Item Type:Conference or Workshop Item
Additional information:This workshop was held in conjunction with the 7th International Conference for Language Resources and Evaluation (LREC 2010).
Faculty:
Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:
Link to this item:http://purl.utwente.nl/publications/75993
Official URL:http://embots.dfki.de/doc/MMC2010-Proceedings.pdf
Conference URL:http://www.multimodal-corpora.org/mmc10.html
Proceedings URL:http://embots.dfki.de/doc/MMC2010-Proceedings.pdf
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page