UCL Discovery Stage
UCL home » Library Services » Electronic resources » UCL Discovery Stage

Machine Learning Mitigants for Speech Based Cyber Risk

Campi, Marta; Peters, Gareth W; Azzaoui, Nourddine; Matsui, Tomoko; (2021) Machine Learning Mitigants for Speech Based Cyber Risk. IEEE Access , 9 pp. 136831-136860. 10.1109/ACCESS.2021.3117080. Green open access

[thumbnail of Campi_Machine Learning Mitigants for Speech Based Cyber Risk_VoR.pdf]
Preview
PDF
Campi_Machine Learning Mitigants for Speech Based Cyber Risk_VoR.pdf - Published Version

Download (5MB) | Preview

Abstract

Statistical analysis of speech is an emerging area of machine learning. In this paper, we tackle the biometric challenge of Automatic Speaker Verification (ASV) of differentiating between samples generated by two distinct populations of utterances, those of an authentic human voice and those generated by a synthetic one. Solving such an issue through a statistical perspective foresees the definition of a decision rule function and a learning procedure to identify the optimal classifier. Classical state-of-the-art countermeasures rely on strong assumptions such as stationarity or local-stationarity of speech that may be atypical to encounter in practice. We explore in this regard a robust non-linear and non-stationary signal decomposition method known as the Empirical Mode Decomposition combined with the Mel-Frequency Cepstral Coefficients in a novel fashion with a refined classifier technique known as multi-kernel Support Vector machine. We undertake significant real data case studies covering multiple ASV systems using different datasets, including the ASVSpoof 2019 challenge database. The obtained results overwhelmingly demonstrate the significance of our feature extraction and classifier approach versus existing conventional methods in reducing the threat of cyber-attack perpetrated by synthetic voice replication seeking unauthorised access.

Type: Article
Title: Machine Learning Mitigants for Speech Based Cyber Risk
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ACCESS.2021.3117080
Publisher version: https://doi.org/10.1109/ACCESS.2021.3117080
Language: English
Additional information: This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
Keywords: Science & Technology, Technology, Computer Science, Information Systems, Engineering, Electrical & Electronic, Telecommunications, Computer Science, Engineering, Feature extraction, Biometrics (access control), Time-frequency analysis, Support vector machines, Task analysis, Standards, Cyberattack, empirical mode decomposition, support vector machine, speech analysis, EMPIRICAL MODE DECOMPOSITION, SPEAKER VERIFICATION, SYNTHESIS SYSTEM, RECOGNITION, COUNTERMEASURES, FEATURES
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Mathematics
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
URI: https://discovery-pp.ucl.ac.uk/id/eprint/10147376
Downloads since deposit
1,188Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item