14 papers
Sparsity-Inducing Divergence Losses for Biometric Verification
Dimitrios Koutsianos, Ladislav Mošner, Yannis Panagakis +1
Performance in face and speaker verification is largely driven by margin-penalty softmax losses such as CosFace and ArcFace. Recently introduced -divergence loss functions offe…
SpeakerCard-1M: An Evidence-Grounded Corpus for In-the-Wild Speaker Verification
Junyi Peng, OldÅich Plchot, Xiao Song +9
Modern speaker verification (SV) systems rely on speaker embeddings that are effective but difficult to interpret or query in natural language. Most existing speech-text corpora ta…
Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation
Ioannis Prokopiou, Pantelis Vikatos, Maximos Kaliakatsos-Papakostas +2
Transformer-based architectures have significantly advanced the generation of complex symbolic sequences, yet a significant gap remains in achieving fine-grained, interpretable con…
Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation
Ioannis Prokopiou, Pantelis Vikatos, Maximos Kaliakatsos-Papakostas +2
Transformer-based architectures have significantly advanced the generation of complex symbolic sequences, yet a significant gap remains in achieving fine-grained, interpretable con…
Evaluating voice anonymisation using similarity rank disclosure
Shilpa Chandra, Matteo Pettenò, Nicholas Evans +7
The evaluation of voice anonymisation remains challenging. Current practice relies on automatic speaker verification metrics such as the equal error rate (EER). Performance estimat…
LabelBuddy: An Open Source Music and Audio Language Annotation Tagging Tool Using AI Assistance
Ioannis Prokopiou, Ioannis Sina, Agisilaos Kounelis +2
The advancement of Machine learning (ML), Large Audio Language Models (LALMs), and autonomous AI agents in Music Information Retrieval (MIR) necessitates a shift from static taggin…