In October 2024, Natural Auditory SCEnes in Humans and Machines (NASCE), collaborative projects by Elia Formisano and Bruno Giordano received ERC Synergy funding (8.6 M€) NASCE integrates AI and multimodal imaging to uncover how the brain transforms everyday soundscapes into meaningful representations of the world (read more here). We will be hiring soon!. Launching in April 2025, NASCE will significantly expand research facilities in Maastricht and Marseille. We are looking for talented PhD students and postdocs interested in AI, and auditory neuroscience to join our team. If you’re passionate about research and ready to take on this exciting challenge, we’d love to hear from you!
This work - published in IEEE Access (Open Access) - offers a comprehensive analysis of many audio-language datasets used to train audio-language models, examining dataset origins, audio-linguistic characteristics, and use cases. An extremely useful resource if you are working on or planning to work in audio-language AI models. Read the full publication here: https://ieeexplore.ieee.org/document/10854210?source=authoralert . Code for downloading and analyzing the datasets here: https://github.com/GLJS/audio-datasets