I'm in South Korea to attend #ismir2025, and after wandering around Seoul for a day, looking at signs, I think I've learned to read Korean, without learning any words!
I remember being told once that Hangul, the system for writing Korean, was designed to be easy to learn, with symbols illustrating how the mouth is positioned to make the corresponding sound. I'm not sure; I haven't checked, and seeing how much I can learn just by looking at bilingual station signs has become a game I'm playing.
From Sunday on, the annual #ISMIR2025 conference is taking place in Daejeon. #Deezer is a proud sponsor of the event since 2018 and this year again, there will be many opportunities to meet and talk with Deezer Researchers: Benjamin Martin Gabriel Meseguer Brocal Kamil Akesbi Yuexuan Kong. Things with the Tutorial session T2 Sunday 21/09 09:00. With "Self-supervised Learning for Music - An Overview and New Horizons" course by Julien Guinot, Alain Riou, Yuexuan Kong, Marco Pasini, Gabriel Meseguer Brocal and Stefan Lattner Then on Monday, no less than three papers will be presented: * "AI-Generated Song Detection via Lyrics Transcripts": session 1, Monday 22/09 09:00 by Markus Frohmann Elena E., Gabriel Meseguer Brocal, Markus Schedl and Romain H. * , "PeakNetFP: Peak-based Neural Audio Fingerprinting Robust to Extreme Time Stretching": session 2, Monday 22/09 14:30 by Guillem C. Benjamin Martin, Emilio Molina Martínez, Xavier Serra and Romain H. * "Emergent musical properties of a transformer under contrastive self-supervised learning": session 2, Monday 22/09 14:30 by Yuexuan Kong, Gabriel Meseguer Brocal Vincent Lostanlen Mathieu Lagrange and Romain H. And don't miss the musical session which is curated by our own Gabriel Meseguer Brocal and our good friend Harin Lee Our fourth paper "A Fourier Explanation of AI-music Artifacts" by Darius A. Gabriel Meseguer Brocal Kamil Akesbi and Romain H., will be presented in session 7, Thursday 25/09 09:00. Later in the day, you'll find our LBD poster "STOMP! Self-supervised beat induction by matching pulses" by Yuexuan Kong Vincent Lostanlen and Gabriel Meseguer Brocal As always, you'll find the papers and lins to code and data on our website: https://lnkd.in/eBk3FJeJ
12th International Conference on Digital Libraries for Musicology
📍 Sogang University, Seoul
📅 26/09/2025
In association with #ISMIR2025, DLfM invites papers on digital libraries, MIR, music encodings, and cultural heritage. Hybrid format; in-person encouraged.
Deadline (EXTENDED): 16/05/2025
#DigitalHumanities #Musicology #MIR #ISMIR #DigitalMusicology #ComputationalMusicology #ComputationalMusicProcessing
🚀 CfP: Human-Centric Music IR (HCMIR) 2025 🚀
Join us at HCMIR, a satellite workshop of ISMIR 2025, exploring ethics, UX/UI, AI collaboration & more in MIR!
📅 Submission opens: June 2, 2025
📌 Deadline: June 18, 2025
🔗 Details: https://sites.google.com/view/hcmir25/
A half-day workshop bringing together researchers, practitioners, and artists to explore the ethical, societal, and human-centred dimensions of MIR Music and technology have long intertwined, transforming how we create, share, and experience music. From composition to listening, advancements in
26th International Society for Music Information Retrieval Conference (#ISMIR2025)
🗓️ 21–25 September 2025 | 📍 Daejeon, Korea & Online
ISMIR 2025 invites contributions in all areas of #MusicInformationRetrieval, including computational music analysis, algorithms, and applications. Topics include #MIRfundamentals, #MachineLearning, #ComputationalEthnomusicology, and #MusicAI.
Deadline: 21/03/2025
#Musicology #CognitiveScience #MusicTechnology #DataScience #ISMIR
Jordan B. L. Smith
Deezer Research
Petr Nuska
musiconn
Lorenzo Porcaro (@RecSys25)