Breaking Resource Barriers in Speech Emotion Recognition via Data Distillation
This work addresses resource and privacy constraints for speech emotion recognition in IoT applications, but it is incremental as it applies an existing technique to a specific domain.
The paper tackled the challenges of limited resources and privacy in speech emotion recognition for IoT edge devices by proposing a data distillation framework, achieving performance comparable to models trained on the original full dataset.
Speech emotion recognition (SER) plays a crucial role in human-computer interaction. The emergence of edge devices in the Internet of Things (IoT) presents challenges in constructing intricate deep learning models due to constraints in memory and computational resources. Moreover, emotional speech data often contains private information, raising concerns about privacy leakage during the deployment of SER models. To address these challenges, we propose a data distillation framework to facilitate efficient development of SER models in IoT applications using a synthesised, smaller, and distilled dataset. Our experiments demonstrate that the distilled dataset can be effectively utilised to train SER models with fixed initialisation, achieving performances comparable to those developed using the original full emotional speech dataset.