Innovations in Urban Sound Event Detection and Annotation

Created using ChatSlide

Explore the 'Introduction to Urban Sound Dataset', a project submitted with guidance from supervisors Gan Woon Seng, focusing on multi-modal data techniques. It details dataset collection involving 360-degree video and audio setups, with structured annotations for Sound Event Localisation and Detection (SELD). Discover automated synchronisation techniques using clap detection and MoviePy for video optimisations. Delve into sound event classification employing the YAMNet pre-trained model and...