EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Voice spoofing detection using a neural networks assembly considering spectrograms and mel frequency cepstral coefficients

Carlos Alberto Hernández-Nava iD, Eric Alfredo Rincón-García, Pedro Lara-Velázquez, Sergio Gerardo de-Los-Cobos-Silva, Miguel Angel Gutiérrez-Andrade, Roman Anselmo Mora-Gutiérrez

PeerJ Computer Science · 18.12.2023 · 9 · e1740

DOI: 10.7717/peerj-cs.1740 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 18.12.2023. Verfasst von Carlos Alberto Hernández-Nava und 5 weiteren Autor:innen. Beteiligte Einrichtung: Posgrado en Ciencias y Tecnologías de la Información, Universidad Autónoma Metropolitana, Ciudad de México, Ciudad de México, México. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Autonomous Metropolitan University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Nowadays, biometric authentication has gained relevance due to the technological advances that have allowed its inclusion in many daily-use devices. However, this same advantage has also brought dangers, as spoofing attacks are now more common. This work addresses the vulnerabilities of automatic speaker verification authentication systems, which are prone to attacks arising from new techniques for the generation of spoofed audio. In this article, we present a countermeasure for these attacks using an approach that includes easy to implement feature extractors such as spectrograms and mel frequency cepstral coefficients, as well as a modular architecture based on deep neural networks. Finally, we evaluate our proposal using the well-know ASVspoof 2017 V2 database, the experiments show that using the final architecture the best performance is obtained, achieving an equal error rate of 6.66% on the evaluation set.

Schlagwörter

Stichwörter der Autor:innen

AssemblyDeep neural networksMel Frequency Cepstral CoefficientsSpectrogramsSpoof detection

Autor:innen und Institutionen

  • Posgrado en Ciencias y Tecnologías de la Información, Universidad Autónoma Metropolitana, Ciudad de México, Ciudad de México, México.
  • Departamento de Ingeniería Eléctrica, Universidad Autónoma Metropolitana, Ciudad de México, Ciudad de México, México.
  • Departamento de Sistemas, Universidad Autónoma Metropolitana de Azcapotzalco, Ciudad de México, Ciudad de México, México.

ORCID-Profile: Carlos Alberto Hernández-Nava

Förderung

  • Autonomous Metropolitan University

Zitieren

APA

Hernández-Nava, C. A., Rincón-García, E. A., Lara-Velázquez, P., de-Los-Cobos-Silva, S. G., Gutiérrez-Andrade, M. A., & Mora-Gutiérrez, R. A. (2023). Voice spoofing detection using a neural networks assembly considering spectrograms and mel frequency cepstral coefficients. PeerJ Computer Science, 9, e1740. https://doi.org/10.7717/peerj-cs.1740

Vancouver

Hernández-Nava CA, Rincón-García EA, Lara-Velázquez P, de-Los-Cobos-Silva SG, Gutiérrez-Andrade MA, Mora-Gutiérrez RA. Voice spoofing detection using a neural networks assembly considering spectrograms and mel frequency cepstral coefficients. PeerJ Computer Science. 2023;9:e1740. doi:10.7717/peerj-cs.1740

BibTeX
@article{HernndezNava2023,
  author = {Hernández-Nava, Carlos Alberto and Rincón-García, Eric Alfredo and Lara-Velázquez, Pedro and de-Los-Cobos-Silva, Sergio Gerardo and Gutiérrez-Andrade, Miguel Angel and Mora-Gutiérrez, Roman Anselmo},
  title = {Voice spoofing detection using a neural networks assembly considering spectrograms and mel frequency cepstral coefficients},
  journal = {PeerJ Computer Science},
  year = {2023},
  volume = {9},
  pages = {e1740},
  doi = {10.7717/peerj-cs.1740}
}
Kostenlos starten →