Analyzing the Direction of Emotional Influence in Nonverbal Dyadic Communication: A Facial-Expression Study

Shadaydeh, Maha; Müller, Lea; Schneider, Dana; Thümmel, Martin; Kessler, Thomas; Denzler, Joachim

doi:10.1109/access.2021.3078195

Cited by 6 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, these methods can offer benefits to clinical diagnosis and intervention, such as in the fields of autism [ 2 , 3 ], prognosis and prevention (e.g., in the detection of depression or suicidal tendencies [ 4 , 5 ], or even in the context of therapies and human conflict resolution [ 6 , 7 , 8 ]. Such methods may also support better understanding of temporal causality of nonverbal behavior in dyadic human social interactions [ 9 ] or help to provide a non-invasive yet objective assessment of imitation behavior [ 10 , 11 ]. In the context of robotics and HCI, and especially when combined with high-quality speech synthesis technology [ 12 ], efficient emotion recognition algorithms can also contribute to experiencing interactions with robot or other technological devices as rewarding, seamless and trustworthy.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Machine Learning Algorithms and Feature Sets for Automatic Vocal Emotion Recognition in Speech

Doğdu

Kessler

Schneider

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Vocal emotion recognition (VER) in natural speech, often referred to as speech emotion recognition (SER), remains challenging for both humans and computers. Applied fields including clinical diagnosis and intervention, social interaction research or Human Computer Interaction (HCI) increasingly benefit from efficient VER algorithms. Several feature sets were used with machine-learning (ML) algorithms for discrete emotion classification. However, there is no consensus for which low-level-descriptors and classifiers are optimal. Therefore, we aimed to compare the performance of machine-learning algorithms with several different feature sets. Concretely, seven ML algorithms were compared on the Berlin Database of Emotional Speech: Multilayer Perceptron Neural Network (MLP), J48 Decision Tree (DT), Support Vector Machine with Sequential Minimal Optimization (SMO), Random Forest (RF), k-Nearest Neighbor (KNN), Simple Logistic Regression (LOG) and Multinomial Logistic Regression (MLR) with 10-fold cross validation using four openSMILE feature sets (i.e., IS-09, emobase, GeMAPS and eGeMAPS). Results indicated that SMO, MLP and LOG show better performance (reaching to 87.85%, 84.00% and 83.74% accuracies, respectively) compared to RF, DT, MLR and KNN (with minimum 73.46%, 53.08%, 70.65% and 58.69% accuracies, respectively). Overall, the emobase feature set performed best. We discuss the implications of these findings for applications in diagnosis, intervention or HCI.

show abstract