My name is Ali Ahmadi Katamjani, and I began my PhD in June 2025 at Utrecht 木瓜福利影视, within the HAICu project, focusing on the Research topic: 鈥淎udio and multimodal feature learning beyond words.鈥 It focuses on building innovative machine learning models for multimodal and emotion-aware search in broadcast archives, using audio, speech, music, and other non-verbal features. I鈥檓 especially interested in how we can move beyond text to understand meaning in cultural heritage collections.
I hold both a . and . in Computer Engineering and Software Engineering from the 木瓜福利影视 of Guilan, Iran, where I specialized in deep learning, time series, and music information retrieval. My master鈥檚 thesis focused on Persian classical music and contributed a new dataset and methodology for instrument classification. Outside of research, I enjoy hiking, playing guitar, and exploring the intersection of music and technology.