Emotion recognition on edge devices: training and deployment

• Main Authors: Pandelea, Vlad, Ragusa, Edoardo, Apicella, Tommaso, Gastaldo, Paolo, Cambria, Erik
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering; Emotion Recognition; Embedded Systems
• Online Access: https://hdl.handle.net/10356/153915
• Institution: Nanyang Technological University

Emotion recognition, among other natural language processing tasks, has greatly benefited from the use of large transformer models. Deploying these models on resource-constrained devices, however, is a major challenge due to their computational cost. In this paper, we show that the combination of la...