4 papers
Switchboard-Affect: Emotion Perception Labels from Conversational Speech
Amrit Romana, Jaya Narain, Tien Dung Tran +4
Understanding the nuances of speech emotion dataset curation and labeling is essential for assessing speech emotion recognition (SER) model potential in real-world applications. Mo…
Affect Models Have Weak Generalizability to Atypical Speech
Jaya Narain, Amrit Romana, Vikramjit Mitra +2
Speech and voice conditions can alter the acoustic properties of speech, which could impact the performance of paralinguistic models for affect for people with atypical speech. We…
Modeling speech emotion with label variance and analyzing performance across speakers and unseen acoustic conditions
Vikramjit Mitra, Amrit Romana, Dung T. Tran +1
Spontaneous speech emotion data usually contain perceptual grades where graders assign emotion score after listening to the speech files. Such perceptual grades introduce uncertain…
Rethinking Emotion Annotations in the Era of Large Language Models
Minxue Niu, Yara El-Tawil, Amrit Romana +1
Modern affective computing systems rely heavily on datasets with human-annotated emotion labels, for training and evaluation. However, human annotations are expensive to obtain, se…