Discernment

Comprehension of Synthetic and Natural Speech: Differences among Sighted and Visually Impaired Young Adults 


Konstantinos Papadopoulos and Eleni Koustriava

2015

Accessibility, Greek, Discernment


The present study examines the comprehension of texts presented via synthetic and natural speech in individuals with and without visual impairments. Twenty adults with visual impairments and 65 sighted adults participated in the study.

Deepfake Defense: Constructing and Evaluating a Specialized Urdu Deepfake Audio Dataset


Sheza Munir, Wassay Sajjad, Mukeet Raza, Emaan Mujahid Abbas, Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha Ali Raza

2023

Discernment, Detection, Dataset, Urdu


This paper addresses the escalating challenges posed by deepfake attacks on Automatic Speaker Verification (ASV) systems. We present a novel Urdu deepfake audio dataset for deepfake detection, focusing on two spoofing attacks – Tacotron and VITS TTS.

Evaluating Comprehension of Natural and Synthetic Conversational Speech


Mirjam Wester, Oliver Watts and Gustav Eje Henter

2016

AI x Human Dialogue, Discernment, English


In an effort to develop more ecologically relevant evaluation techniques that go beyond isolated sentences, this paper investigates comprehension of natural and synthetic speech dialogues.

Generation and Detection of Sign Language Deepfakes – A Linguistic and Visual Analysis


Shahzeb Nacem, Muhammad Riyyan Khan, Usman Tariq, Abhinav Dhall, Carlos Ivan Colon, Hasan Al-Nashash

2024

Generation, Discernment, Detection, Dataset, Accessibility, American Sign Language


This research presents a positive application of deepfake technology in upper body generation, while performing sign-language for the Deaf and Hard of Hearing (DHoH) community.

Uncovering Human Traits in Determining Real and Spoofed Audio: Insights from Blind and Sighted Individuals


Chaeeun Han, Prasenjit Mitra, Syed Masum Billah

2024

Discernment, Accessibility, English


This paper explores how blind and sighted individuals perceive real and spoofed audio, highlighting differences and similarities between the groups.

NSF Award #2346473