Privacy Enhanced Speech Emotion Communication using Deep Learning Aided Edge Computing
Paper
Paper/Presentation Title | Privacy Enhanced Speech Emotion Communication using Deep Learning Aided Edge Computing |
---|---|
Presentation Type | Paper |
Authors | Ali, Hafiz Shehbaz (Author), Hassan, Fakhar ul (Author), Latif, Siddique (Author), Manzoor, Habib Ullah (Author) and Qadir, Junaid (Author) |
Journal or Proceedings Title | 2021 IEEE International Conference on Communications Workshops (ICC Workshops) Proceedings |
ERA Conference ID | 42928 |
Number of Pages | 5 |
Year | 2021 |
Place of Publication | United States |
ISBN | 9781728194417 |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ICCWorkshops50388.2021.9473669 |
Web Address (URL) of Paper | https://ieeexplore.ieee.org/document/9473669 |
Conference/Event | IEEE International Conference on Communications Workshops (2021) |
IEEE International Conference on Communications | |
Event Details | IEEE International Conference on Communications ICC Rank B B B B B B B B B B |
Event Details | IEEE International Conference on Communications Workshops (2021) Event Date 14 to end of 23 Jun 2021 Event Location Montreal, Canada |
Abstract | Speech emotion sensing in communication networks has a wide range of applications in real life. In these applications, voice data are transmitted from the user to the central server for storage, processing, and decision making. However, speech data contain vulnerable information that can be used maliciously without the user's consent by an eavesdropping adversary. In this work, we present a privacy-enhanced emotion communication system for preserving the user personal information in emotion-sensing applications. We propose the use of an adversarial learning framework that can be deployed at the edge to unlearn the users' private information in the speech representations. These privacy-enhanced representations can be transmitted to the central server for decision making. We evaluate the proposed model on multiple speech emotion datasets and show that the proposed model can hide users' specific demographic information and improve the robustness of emotion identification without significantly impacting performance. To the best of our knowledge, this is the first work on a privacy-preserving framework for emotion sensing in the communication network. |
Keywords | emotion communication system, speech emotionrecognition, privacy enhanced features, deep learning, edgecomputing. |
ANZSRC Field of Research 2020 | 461101. Adversarial machine learning |
461106. Semi- and unsupervised learning | |
461103. Deep learning | |
461104. Neural networks | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Emulation AI, Australia |
Information Technology University, Pakistan | |
University of Southern Queensland | |
University of Engineering and Technology, Pakistan | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q6y87/privacy-enhanced-speech-emotion-communication-using-deep-learning-aided-edge-computing
69
total views4
total downloads3
views this month0
downloads this month