6 citations · 6 across the 8 of their papers we have counts for
9 papers
OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL
Karl El Hajal, Mathew Magimai. -Doss
We propose Online Latent prediction with Invariant Views and rEconstruction (OLIVE), a self-supervised speech representation learning framework that jointly optimizes analysis and…
Toward using Speech to Sense Student Emotion in Remote Learning Environments
Sargam Vyas, Bogdan Vlasenko, André Mayoraz +3
With advancements in multimodal communication technologies, remote learning environments such as, distance universities are increasing. Remote learning typically happens asynchrono…
Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing
Panagiotis Theocharopoulos, Ajinkya Kulkarni, Mathew Magimai. -Doss
Large language models (LLMs) are increasingly considered for use in high-impact workflows, including academic peer review. However, LLMs are vulnerable to document-level hidden pro…
Assessment of Personality Dimensions Across Situations in Dyadic Role-Play Scenarios
Alice Zhang, Skanda Muralidhar, Daniel Gatica-Perez +1
Prior research indicates that users prefer assistive technologies whose personalities align with their own. This has sparked interest in automatic personality perception (APP), whi…
Unveiling Audio Deepfake Origins: A Deep Metric learning And Conformer Network Approach With Ensemble Fusion
Ajinkya Kulkarni, Sandipana Dowerah, Tanel Alumae +1
Audio deepfakes are acquiring an unprecedented level of realism with advanced AI. While current research focuses on discerning real speech from spoofed speech, tracing the source s…
Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech
Karl El Hajal, Enno Hermann, Sevada Hovsepyan +1
Automatic speech recognition (ASR) systems struggle with dysarthric speech due to high inter-speaker variability and slow speaking rates. To address this, we explore dysarthric-to-…
Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR
Karl El Hajal, Enno Hermann, Ajinkya Kulkarni +1
Automatic speech recognition (ASR) systems are well known to perform poorly on dysarthric speech. Previous works have addressed this by speaking rate modification to reduce the mis…
kNN Retrieval for Simple and Effective Zero-Shot Multi-speaker Text-to-Speech
Karl El Hajal, Ajinkya Kulkarni, Enno Hermann +1
While recent zero-shot multi-speaker text-to-speech (TTS) models achieve impressive results, they typically rely on extensive transcribed speech datasets from numerous speakers and…
Towards interfacing large language models with ASR systems using confidence measures and prompting
Maryam Naderi, Enno Hermann, Alexandre Nanchen +2
As large language models (LLMs) grow in parameter size and capabilities, such as interaction through prompting, they open up new ways of interfacing with automatic speech recogniti…