The uulmMAC Database-A Multimodal Affective Corpus for Affective Computing in Human-Computer Interaction

ADABase: A Multimodal Dataset for Cognitive Load Estimation

Driver monitoring systems play an important role in lower to mid-level autonomous vehicles. Our work focuses on the detection of cognitive load as a component of driver-state estimation to improve traffic safety. By inducing single and dual-task workloads of increasing intensity on 51 subjects, while continuously measuring signals from multiple modalities, based on physiological measurements such as ECG, EDA, EMG, PPG, respiration rate, skin temperature and eye tracker data, as well as behavioral measurements such as action units extracted from facial videos, performance metrics like reaction time and subjective feedback using questionnaires, we create ADABase (Autonomous Driving Cognitive Load Assessment Database) As a reference method to induce cognitive load onto subjects, we use the well-established n-back test, in addition to our novel simulator-based k-drive test, motivated by real-world semi-autonomously vehicles. We extract expert features of all measurements and find significant changes in multiple modalities. Ultimately we train and evaluate machine learning algorithms using single and multimodal inputs to distinguish cognitive load levels. We carefully evaluate model behavior and study feature importance. In summary, we introduce a novel cognitive load test, create a cognitive load database, validate changes using statistical tests, introduce novel classification and regression tasks for machine learning and train and evaluate machine learning models.

Multi-Path and Group-Loss-Based Network for Speech Emotion Recognition in Multi-Domain Datasets

Speech emotion recognition (SER) is a natural method of recognizing individual emotions in everyday life. To distribute SER models to real-world applications, some key challenges must be overcome, such as the lack of datasets tagged with emotion labels and the weak generalization of the SER model for an unseen target domain. This study proposes a multi-path and group-loss-based network (MPGLN) for SER to support multi-domain adaptation. The proposed model includes a bidirectional long short-term memory-based temporal feature generator and a transferred feature extractor from the pre-trained VGG-like audio classification model (VGGish), and it learns simultaneously based on multiple losses according to the association of emotion labels in the discrete and dimensional models. For the evaluation of the MPGLN SER as applied to multi-cultural domain datasets, the Korean Emotional Speech Database (KESD), including KESDy18 and KESDy19, is constructed, and the English-speaking Interactive Emotional Dyadic Motion Capture database (IEMOCAP) is used. The evaluation of multi-domain adaptation and domain generalization showed 3.7% and 3.5% improvements, respectively, of the F1 score when comparing the performance of MPGLN SER with a baseline SER model that uses a temporal feature generator. We show that the MPGLN SER efficiently supports multi-domain adaptation and reinforces model generalization.

Arousal Detection in Elderly People from Electrodermal Activity Using Musical Stimuli

The detection of emotions is fundamental in many areas related to health and well-being. This paper presents the identification of the level of arousal in older people by monitoring their electrodermal activity (EDA) through a commercial device. The objective was to recognize arousal changes to create future therapies that help them to improve their mood, contributing to reduce possible situations of depression and anxiety. To this end, some elderly people in the region of Murcia were exposed to listening to various musical genres (flamenco, Spanish folklore, Cuban genre and rock/jazz) that they heard in their youth. Using methods based on the process of deconvolution of the EDA signal, two different studies were carried out. The first, of a purely statistical nature, was based on the search for statistically significant differences for a series of temporal, morphological, statistical and frequency features of the processed signals. It was found that Flamenco and Spanish Folklore presented the highest number of statistically significant parameters. In the second study, a wide range of classifiers was used to analyze the possible correlations between the detection of the EDA-based arousal level compared to the participants' responses to the level of arousal subjectively felt. In this case, it was obtained that the best classifiers are support vector machines, with 87% accuracy for flamenco and 83.1% for Spanish Folklore, followed by K-nearest neighbors with 81.4% and 81.5% for Flamenco and Spanish Folklore again. These results reinforce the notion of familiarity with a musical genre on emotional induction.