Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Balancing Privacy and Accuracy in Federated Learning for Speech Emotion Recognition
RISE Research Institutes of Sweden, Digital Systems, Industrial Systems.ORCID iD: 0000-0003-4725-0595
RISE Research Institutes of Sweden, Digital Systems, Industrial Systems. University of Padua, Italy.ORCID iD: 0000-0002-8470-3277
RISE Research Institutes of Sweden, Digital Systems, Industrial Systems.ORCID iD: 0000-0001-5951-9374
Mälardalen University, Sweden.ORCID iD: 0000-0002-4473-7763
Show others and affiliations
2023 (English)In: ACSIS Annals of Computer Science and Information Systems, Vol. 35, p. 191-199Article in journal (Refereed) Published
Abstract [en]

Context: Speech Emotion Recognition (SER) is a valuable technology that identifies human emotions from spoken language, enabling the development of context-aware and personalized intelligent systems. To protect user privacy, Federated Learning (FL) has been introduced, enabling local training of models on user devices. However, FL raises concerns about the potential exposure of sensitive information from local model parameters, which is especially critical in applications like SER that involve personal voice data. Local Differential Privacy (LDP) has prevented privacy leaks in image and video data. However, it encounters notable accuracy degradation when applied to speech data, especially in the presence of high noise levels. In this paper, we propose an approach called LDP-FL with CSS, which combines LDP with a novel client selection strategy (CSS). By leveraging CSS, we aim to improve the representatives of updates and mitigate the adverse effects of noise on SER accuracy while ensuring client privacy through LDP. Furthermore, we conducted model inversion attacks to evaluate the robustness of LDP-FL in preserving privacy. These attacks involved an adversary attempting to reconstruct individuals' voice samples using the output labels provided by the SER model. The evaluation results reveal that LDP-FL with CSS achieved an accuracy of 65-70%, which is 4% lower than the initial SER model accuracy. Furthermore, LDP-FL demonstrated exceptional resilience against model inversion attacks, outperforming the non-LDP method by a factor of 10. Overall, our analysis emphasizes the importance of achieving a balance between privacy and accuracy in accordance with the requirements of the SER application.

Place, publisher, year, edition, pages
2023. Vol. 35, p. 191-199
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:ri:diva-68535DOI: 10.15439/2023F444OAI: oai:DiVA.org:ri-68535DiVA, id: diva2:1819079
Conference
2023 18th Conference on Computer Science and Intelligence Systems (FedCSIS)
Note

This work was partially supported by EU ECSEL projectDAIS that has received funding from the ECSEL Joint Undertaking (JU) under grant agreement No.101007273.

Available from: 2023-12-13 Created: 2023-12-13 Last updated: 2024-03-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Authority records

Mohammadi, SamanehMohammadi, MohammadrezaSinaei, SimaBalador, Ali

Search in DiVA

By author/editor
Mohammadi, SamanehMohammadi, MohammadrezaSinaei, SimaBalador, Ali
By organisation
Industrial Systems
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 19 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf