Version 1
: Received: 16 September 2024 / Approved: 16 September 2024 / Online: 16 September 2024 (16:46:29 CEST)
How to cite:
Saraiva, A.; Fejes, A.; Devenson, J. Impact of face masks on acoustic parameters for Forensic Speaker Recognition. Preprints2024, 2024091261. https://doi.org/10.20944/preprints202409.1261.v1
Saraiva, A.; Fejes, A.; Devenson, J. Impact of face masks on acoustic parameters for Forensic Speaker Recognition. Preprints 2024, 2024091261. https://doi.org/10.20944/preprints202409.1261.v1
Saraiva, A.; Fejes, A.; Devenson, J. Impact of face masks on acoustic parameters for Forensic Speaker Recognition. Preprints2024, 2024091261. https://doi.org/10.20944/preprints202409.1261.v1
APA Style
Saraiva, A., Fejes, A., & Devenson, J. (2024). Impact of face masks on acoustic parameters for Forensic Speaker Recognition. Preprints. https://doi.org/10.20944/preprints202409.1261.v1
Chicago/Turabian Style
Saraiva, A., Attila Fejes and Jelena Devenson. 2024 "Impact of face masks on acoustic parameters for Forensic Speaker Recognition" Preprints. https://doi.org/10.20944/preprints202409.1261.v1
Abstract
The present study investigated how two types of face masks affected seven acoustic parameters, commonly used in forensic speaker recognition, in several languages. Reading samples from an excerpt of “The Little Prince” were recorded by volunteers of both genders speaking in Lithuanian, Croatian, Romanian, Turkish, Ukrainian, Portuguese, Georgian, Hungarian, Spanish, Russian, Polish, and German, without a protection mask, wearing a surgical mask, and wearing an FFP2 mask. In addition, recordings from mobile and landline communications in some of the mentioned languages were also obtained. A total of 860 volunteers were recorded. The dataset is part of the Forensic Multilingual Voices Database (FMVD), developed under the “Competency, Education, Research, Testing, Accreditation, and Innovation in Forensic Science” (CERTAIN-FORS) project, funded by the European Union (EU) and coordinated by the European Network of Forensic Science Institutes (ENFSI). The results showed that face masks have an impact on the studied acoustic parameters and that the effects vary with mask type, sex, language, and recording channel.
Keywords
forensic speaker recognition; face mask; acoustic-phonetic approach
Subject
Engineering, Electrical and Electronic Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.