8 papers
On the Robustness of Audio Deepfake Detection under Audio Watermarking
Zi Qian Yong, Ajinkya Kulkarni, Julia Lau +4
Recent advances in generative audio models have enabled highly realistic synthetic speech, increasing the importance of reliable audio deepfake detection (ADD) systems. While prior…
Paper Pilot: A Human-in-the-Loop Expert System for Evidence-Traceable Scientific Manuscript Generation in Applied Sciences
Nidhi Jha, Siddharth Chaudhary, Ajinkya Kulkarni
Large language model (LLM) agents are increasingly embedded in scientific workflows for literature analysis, drafting, and review. Existing systems advance autonomous discovery and…
Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR
Ajinkya Kulkarni, Sandipana Dowerah, Atharva Kulkarni +2
Self-supervised learning (SSL) underpins modern audio deepfake detection, yet most prior work centers on a single large wav2vec2-XLSR backbone, leaving compact under studied. We pr…
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…
Children's Voice Privacy: First Steps And Emerging Challenges
Ajinkya Kulkarni, Francisco Teixeira, Enno Hermann +3
Children are one of the most under-represented groups in speech technologies, as well as one of the most vulnerable in terms of privacy. Despite this, anonymization techniques targ…
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 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…