neobjavljeni prilog sa skupa
This study investigates the acoustic and linguistic features associated with deception by analyzing speech from the participants. Each participant narrates three stories: one fabricated, one truthful with a negative emotional tone, and one truthful with a positive emotional tone. The study aims to identify patterns in vocal and linguistic cues that distinguish deceptive speech from truthful speech across varying emotional contexts. Acoustic parameters such as pitch (fundamental frequency), intensity (loudness), speech rate, and pauses will be measured to detect potential vocal stress and cognitive load differences. Linguistic analysis will focus on sentence complexity, word choice, and the use of personal pronouns and affective language.
Preliminary hypotheses suggest that deceptive speech will exhibit increased pitch variability, reduced speech rate, and more frequent disfluencies compared to truthful speech. Additionally, stories with negative emotions may display unique vocal stress markers, while those with positive emotions may show increased fluency and fewer vocal markers of stress. Data will be analyzed using machine learning algorithms to determine whether these features can reliably predict deception. This work aims to enhance our understanding of how emotional context influences deceptive speech and contribute to the development of more accurate, voice-based lie detection systems. The results are expected to provide insights into how emotional states modulate speech characteristics in both deceptive and truthful contexts, highlighting the interplay between emotional arousal and cognitive load during deceptive behavior.
audio forensics, forensic linguistics, lie detection, machine learning, Large Language Models
Razvojem virtualizacijskih tehnologija raste kompleksnost IT sustava, dok korisnici istovremeno zahtijevaju brži pristup resursima, napredne integracije i jednostavnost korištenja. Jedno od ključnih rješenja za ove izazove primjena je…
Ovaj rad istražuje i uspoređuje mogućnosti prosljeđivanja grafičkih kartica na Hyper-V i KVM hipervizorima prema virtualnim strojevima, detaljno opisujući metode, postupke i razlike u arhitekturi koje utječu na…
The ever-growing usage and adaptation of HTTP/3 in web traffic leverages Quick UDP Internet Connections (QUIC) as a transport protocol. QUIC is widely recognized for reduced latency, enhanced…
