Results 61 to 70 of about 209 (151)
Likelihood ratios for changepoints in categorical event data with applications in digital forensics
Abstract We investigate likelihood ratio models motivated by digital forensics problems involving time‐stamped user‐generated event data from a device or account. Of specific interest are scenarios where the data may have been generated by a single individual (the device/account owner) or by two different individuals (the device/account owner and ...
Rachel Longjohn, Padhraic Smyth
wiley +1 more source
Semi-automatic approach utilizing Siamese Neural Network for forensic voice comparison
Forensic Voice Comparison (FVC) remains a critical yet challenging task in digital forensics, often hindered by manual subjectivity, background noise, and speaker variability.
S.G. Kruthika +5 more
doaj +1 more source
Abstract Experiment‐based voice parades often result in low hit‐rates and high false‐alarm rates. One contributing factor may be that the experimental procedures omit elements that might naturally occur in the memory formation process, such as the process of reflection.
Nikolas Pautz +5 more
wiley +1 more source
International survey on voice quality: Forensic practitioners versus voice therapists
In recent years, numerous investigations have focused on voice quality (VQ) for forensic purposes. These studies notwithstanding, we lack an international picture of how VQ is generally understood by forensic practitioners and how it contrasts with the ...
Eugenia San Segundo
doaj
The English Dialects App: The creation of a crowdsourced dialect corpus
In this paper, we present the English Dialects App (EDA) and the English Dialects App Corpus (EDAC). EDA is a free iOS and Android app, launched in January 2016 that features a dialect quiz and dialect recordings.
Adrian Leemann +2 more
doaj +1 more source
Forensic Audio and Voice Analysis: TV Series Reinforce False Popular Beliefs
People’s perception of forensic evidence is greatly influenced by crime TV series. The analysis of the human voice is no exception. However, unlike fingerprints—with which fiction and popular beliefs draw an incorrect parallel—the human voice varies ...
Emmanuel Ferragne +8 more
doaj +1 more source
AudioFakeNet: A Model for Reliable Speaker Verification in Deepfake Audio
Deepfake audio refers to the generation of voice recordings using deep neural networks that replicate a specific individual’s voice, often for deceptive or fraud purposes.
Samia Dilbar +3 more
doaj +1 more source
Expert Methods of Foreign-Language Speakers’ Identification by Speech Prosody
According to the data received from the surveys of the criminal environment in Russia over recent years, there is a substantial growth of the crimes committed by the Tadjik, Uzbek and criminal groups of other ethnical origin.
Irina V. Kuryanova
doaj +1 more source
This paper reports the findings from a multidisciplinary and cross-institutional Economic and Social Research Council (ESRC) funded project called ‘Improving Voice Identification Procedures’ (IVIP).
Alice Paver +3 more
doaj +1 more source
Towards the applicability of voice quality in forensic phonetics
Voice quality derived from long-term laryngeal settings stands out as a potentially individualizing trait of speakers. This places it in an advantageous situation with respect to other phonetic parameters used in forensic linguistics. However, anyone confronted with its analysis will immediately run into a methodological difficulty stemming from its ...
openaire +2 more sources

