Do Synthetic Voices Have Emotions? Exploring Emotional Cues for Spoofed Speech Detection

Research output: Chapter in Book/Report/Conference proceedingsChapterpeer-review

Abstract

Spoofed speech poses a significant threat as it can be used to impersonate people. Spoofed speech can also be used to gain unauthorized access to systems where speech is used as a biometric identifier. It is therefore essential to develop methods that can distinguish bonafide and spoofed speech. Generated speech quality is improving dramatically in recent years and it is necessary to find new effective detection methods. In this work, we analyze the emotion of both, spoofed and bonafide speech from the ASVspoof 2019 dataset using various Speech Emotion Recognition (SER) algorithms. We show that generated (spoofed) speech lacks emotion profiles found in bonafide speech. Thus, SER algorithms can be used for spoofed speech detection and a layer of SER may be added to speech processing systems to safeguard against spoofed speech.

Original languageEnglish
Title of host publication2024 Cyber Research Conference - Ireland, Cyber-RCI 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350390100
DOIs
Publication statusPublished - 2024
Event3rd Cyber Research Conference - Ireland, Cyber-RCI 2024 - Carlow, Ireland
Duration: 25 Nov 2024 → …

Publication series

Name2024 Cyber Research Conference - Ireland, Cyber-RCI 2024

Conference

Conference3rd Cyber Research Conference - Ireland, Cyber-RCI 2024
Country/TerritoryIreland
CityCarlow
Period25/11/24 → …

Keywords

  • Cyber security
  • Speech emotion recognition
  • Speech processing
  • Spoofing attacks

Fingerprint

Dive into the research topics of 'Do Synthetic Voices Have Emotions? Exploring Emotional Cues for Spoofed Speech Detection'. Together they form a unique fingerprint.

Cite this