Conventional emotion classification methods focus on predefined segments such as sentences or speaking turns that are labeled and classified at the segment level. However, the emotional state dynamically fluctuates during human interactions, so not all the segments have the same relevance. We are interested in detecting regions within the interaction where the emotions are particularly salient, which we refer to as emotional hotspots. A system with this capability can have real applications in many domains. A key step towards building such a system is to define reliable hotspot labels, which will dictate the performance of machine learning algorithms. Creating ground-truth labels from scratch is both expensive and time consuming. This paper also demonstrates that defining those emotionally salient segments using perceptual evaluation is a hard problem resulting in low inter-evaluator agreement. Instead, we propose to define emotionally salient regions leveraging existing time-continuous emotional labels. The proposed approach relies on the qualitative agreement (QA) method, which dynamically captures increasing or decreasing trends across emotional traces provided by multiple evaluators. The proposed method is more reliable than just averaging traces across evaluators, providing the flexibility to define hotspots at various reliability levels without having to recollect new perceptual evaluations.
Cite as: Parthasarathy, S., Busso, C. (2016) Defining Emotionally Salient Regions Using Qualitative Agreement Method. Proc. Interspeech 2016, 3598-3602, doi: 10.21437/Interspeech.2016-429
@inproceedings{parthasarathy16_interspeech,
author={Srinivas Parthasarathy and Carlos Busso},
title={{Defining Emotionally Salient Regions Using Qualitative Agreement Method}},
year=2016,
booktitle={Proc. Interspeech 2016},
pages={3598--3602},
doi={10.21437/Interspeech.2016-429}
}