C4DM Seminar: Panagiota Anastasopoulou: Characterizing and exploring large and heterogeneous sound collections: the Freesound case
QMUL, School of Electronic Engineering and Computer Science
Centre for Digital Music Seminar Series
Seminar by: Panagiota Anastasopoulou
Date/time: Wednesday, 8th April 2026, 3 pm
Location: G2, Engineering Building, Mile End
Title: Characterizing and exploring large and heterogeneous sound collections: the Freesound case
Abstract:
The exploration of sound collections is an essential task in sound browsing, analysis and retrieval, yet online audio databases often lack structure and informative characterization. We outline the importance of taxonomies for broad audio content and the role of automatic audio classification through a real-world case study of Freesound, a collaborative online platform that serves divese communities, including sound designers, artists, audio researchers, and music producers. We leverage its existing data for tasks such as train models, deploy taxonomies and other acoustic/semantic descriptors, add search filters, tailor audio analyzers and post-processing, and compute similarity. Beyond the web interface, these functionalities are accessible through the Freesound API whose recent enhancements add features and improve support for third-party applications, which we also review for their interaction with the platform. Our approach draws on insights from usage statistics and user studies to help us understand the content of Freesound and provide iterative feedback on new features. By embedding these tools into existing workflows, the platform and research inform each other, thus supporting both scientific exploration and practical sound retrieval, navigation, discovery, and creativity.
Bio:
Panagiota Anastasopoulou is pursuing her PhD studies at the Universitat Pompeu Fabra (UPF) within the Music Technology Group (MTG) and contributes as a member of the Freesound project. Her research is centered on the tasks of characterizing and retrieving audio from large and heterogeneous sound collections. With a strong foundation in musicology, she brings a humanistic perspective to the technological advancements emerging from her research by considering their practical applications for users and their impact on artistic expression. Beyond her academic pursuits, she is an artist (aka allholy) who continues to create music and actively engages with artistic communities. She is a practitioner of live coding and currently participates in TOPLAP Athens and TOPLAP Barcelona communities.