An engineering view on emotions and speech: From analysis and predictive models to responsible human-centered applications

CC Lee, T Chaspari, EM Provost… - Proceedings of the …, 2023 - ieeexplore.ieee.org
The substantial growth of Internet-of-Things technology and the ubiquity of smartphone
devices has increased the public and industry focus on speech emotion recognition (SER) …

Minority views matter: Evaluating speech emotion classifiers with human subjective annotations by an all-inclusive aggregation rule

HC Chou, L Goncalves, SG Leem… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
When selecting test data for subjective tasks, most studies define ground truth labels using
aggregation methods such as the majority or plurality rules. These methods discard data …

EMO-SUPERB: An in-depth look at speech emotion recognition

H Wu, HC Chou, KW Chang, L Goncalves, J Du… - arxiv preprint arxiv …, 2024 - arxiv.org
Speech emotion recognition (SER) is a pivotal technology for human-computer interaction
systems. However, 80.77% of SER papers yield results that cannot be reproduced. We …

Open-Emotion: A Reproducible EMO-Superb For Speech Emotion Recognition Systems

H Wu, HC Chou, KW Chang… - 2024 IEEE Spoken …, 2024 - ieeexplore.ieee.org
Speech emotion recognition (SER) is an essential technology for human-computer
interaction systems. However, the previous study reveals that 80.77% of SER papers yield …

Estimating the uncertainty in emotion attributes using deep evidential regression

W Wu, C Zhang, PC Woodland - arxiv preprint arxiv:2306.06760, 2023 - arxiv.org
In automatic emotion recognition (AER), labels assigned by different human annotators to
the same utterance are often inconsistent due to the inherent complexity of emotion and the …

Exploiting co-occurrence frequency of emotions in perceptual evaluations to train a speech emotion classifier

HC Chou, CC Lee, C Busso - Interspeech 2022, 2022 - par.nsf.gov
Previous studies on speech emotion recognition (SER) with categorical emotions have often
formulated the task as a single-label classification problem, where the emotions are …

A Primary task driven adaptive loss function for multi-task speech emotion recognition

LY Liu, WZ Liu, L Feng - Engineering Applications of Artificial Intelligence, 2024 - Elsevier
Abstract Although Speech Emotion Recognition (SER) is becoming an active research area,
the state-of-the-art performance is limited by the scarcity of emotional datasets. The …

Personality-assisted mood modeling with historical reviews for sentiment classification

Y Ji, W Wu, Y Hu, X Chen, J Chen, W Hu, L He - Information Sciences, 2023 - Elsevier
Review sentiment classification aims to predict user sentiment for given user-generated
review. Most of the existing methods enhance their sentiment classifiers by incorporating …

Deep temporal clustering features for speech emotion recognition

WC Lin, C Busso - Speech Communication, 2024 - Elsevier
Deep clustering is a popular unsupervised technique for feature representation learning. We
recently proposed the chunk-based DeepEmoCluster framework for speech emotion …

Learning with rater-expanded label space to improve speech emotion recognition

SG Upadhyay, WS Chien, BH Su… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Automatic sensing of emotional information in speech is important for numerous everyday
applications. Conventional Speech Emotion Recognition (SER) models rely on averaging or …