Speaker: Daniel Ramos Castro. Abstract: Probabilistic predictions are vital for decision-making in many applications of machine learning and AI, including medicine, forensics, security, and safety. However, many multiclass classifiers produce poorly calibrated outputs, leading to suboptimal decisions with potentially high… Read More
Titans: Learning to Memorize at Test Time
Speaker: Adrián Aranda Márquez. Abstract: This presentation provides an in-depth analysis of the paper Titans: Learning to Memorize at Test Time, which proposes a novel neural architecture designed to enhance long-term contextual learning in sequence modeling. The authors introduce the Titans… Read More
Calibration and Fusion of End-to-End Neural Diarization Models: A Comprehensive Framework
Speaker: Sergio Álvarez Balanya Abstract: End-to-End Neural Diarization (EEND) systems produce frame-level probabilistic speaker activity estimates, yet the reliability of these confidence scores remains largely unexplored. Unlike hard-decision fusion approaches such as DOVER-Lap, working with continuous probability outputs enables more… Read More
YOLO-based Transfer Learning for Acoustic Event Detection using Visual Object Detection Techniques
Speaker: Sergio Segovia González. Abstract: Traditional SED approaches are based on either specialized models or on these models in combination with general audio embedding extractors. In this article we propose to reframe SED as an object detection task in the… Read More