Iulia Lefter

TL;DR: The INTERSPEECH 2021 Computational Paralinguistics Challenge as discussed by the authors addressed four different problems for the first time in a research competition under well-defined conditions: In the COVID-19 Cough and COVID19 Speech Sub-Challenges, a binary classification on COVID 19 infection has to be made based on coughing sounds and speech; in the Escalation SubChallenge, a three-way assessment of the level of escalation in a dialogue is featured; and in the Primates Subchallenge, four species vs background need to be classified.

TL;DR: It is found that speech modulation is the best performing intermediate level variable for automatic stress prediction and the two-stage approach with intermediate variables performs better than baseline feature level or decision level fusion.

TL;DR: In this paper, the authors describe the design of a system for selecting the calls that appear to be urgent, based on emotion detection, trained using a database of spontaneous emotional speech from a call-centre.

TL;DR: The performance of an emotion detection system tested on a certain database given that it is trained on speech from either the same database, a different database or a mix of both is investigated.

TL;DR: It is proved that the meta-features have a positive effect on the fusion process in terms of labels, and three fusion methods that encapsulate the Meta- Features are compared, based on automatic prediction of the intermediate level variables and multimodal aggression from state of the art low level acoustic, linguistic and visual features.