ISMIR Conference

A field stands on two legs: algorithms & data. Sharing the #ISMIR2025 Classical Test-of-Time Award is the legendary Masataka Goto for his 2006 AIST Annotations for the RWC Database.📜 This work provided THE benchmark dataset for a generation of MIR research. A monumental contribution that enabled progress across the field. A true honor to celebrate this work tonight! #TestOfTime #MIR #OpenData #GroundTruth

Honoring a true classic from the archives! The #ISMIR2025 Classical Test-of-Time Award goes to Meinard Müller et al. for their 2005 paper, "Audio Matching via Chroma-Based Statistical Features." 🎼 This paper introduced a robust chroma feature that revolutionized audio matching for classical music. Two decades later, it remains a pillar of the field. Truly foundational work. Congratulations! #TestOfTime #MIR #ChromaFeatures #ClassicalMusic

As #ISMIR2025 winds down, it's the perfect time to celebrate the ideas that have shaped our field. A huge congratulations to Brian McFee, Eric J. Humphrey, and Juan P. Bello for receiving the 10-Year Test-of-Time Runner-Up award! 🏆⏳ Their 2015 paper, "A Software Framework For Musical Data Augmentation," introduced a concept that is now a cornerstone of modern audio machine learning. By providing a framework to expand datasets with musically-aware perturbations, they paved the way for the robust, data-hungry models we see today. It's hard to imagine training a state-of-the-art audio model now without data augmentation. A truly foundational paper and a well-deserved honor! #ISMIR2025 #TestOfTime #DataAugmentation #MIR #MachineLearning #AudioML

And the winner of the ISMIR 2025 10-Year Test-of-Time Award is... a true landmark in rhythmic analysis! ✨🏆 A huge, heartfelt congratulations to Florian Krebs, Sebastian Böck, and Gerhard Widmer for their paper, "An Efficient State-Space Method for Joint Tempo and Meter Tracking." This work provided a brilliant and elegant "drop-in replacement" for beat and meter tracking systems that achieved a rare triple-win: it was more accurate, drastically faster, and more memory-efficient. A decade later, its influence is still felt in the robust and practical tools our community relies on. This paper set a new standard for a fundamental MIR task. A truly deserving winner! #ISMIR2025 #TestOfTimeAward #BeatTracking #MIR #SignalProcessing #LandmarkPaper

It’s incredibly exciting to see this win the Best Student Paper Award at #ISMIR2025, especially as South Korea was one of the five key regions in their study! A huge congratulations to Harin Lee, Elif Çelen, Peter Harrison, Manuel Anglada Tort, Pol Van Rijn, Minsu Park, Marc Schönwiesner, and Nori Jacoby for their essential work on "GlobalMood: A cross-cultural benchmark for music emotion recognition." They address a major bias in AI by creating a new dataset with music from 59 countries and annotations from diverse cultures (including the U.S., France, Mexico, Egypt, and S. Korea). Their bottom-up approach, which allowed participants to use their own emotion terms, is a game-changer for building AI that truly understands global music.

A huge congratulations to the winners of the Best Student Paper Award at #ISMIR2025! 🏆 Kudos to Ben Hayes, Charalampos Saitis, and György Fazekas for their fantastic work: "Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching." Ever heard a synth sound and wondered how to recreate it? It's a notoriously hard problem because different knob settings can create the same sound. This paper offers a brilliant solution, using generative models that understand a synth's inherent symmetries (like swappable oscillators). Their method significantly outperforms baselines on a complex, real-world synth, Surge XT!

Are AI models for music truly listening, or just good at guessing? This critical question is at the heart of the latest Best Paper Award winner at #ISMIR2025! Huge congratulations to Yongyi Zang, Sean O'brien, Taylor Berg Kirkpatrick, Julian McAuley, and Zachary Novack for their paper, "Are you really listening? Boosting Perceptual Awareness in Music-QA Benchmarks." They expose how current benchmarks can be solved without genuine audio perception—even by text-only models! Their new framework, RUListening, creates evaluations that force models to prove they're actually hearing the music. A vital step forward for robust AI evaluation.

Huge congratulations to Darius Afchar, Gabriel Meseguer Brocal, Kamil Akesbi, and Romain Hennequin for winning the Best Paper Award at #ISMIR2025! 🏆 In their paper, "A Fourier Explanation of AI-music Artifacts," they tackle one of the biggest challenges in generative AI: detection. They mathematically prove that AI models like Suno and Udio leave a fundamental "fingerprint"—tiny, predictable spikes in the frequency spectrum. This allows for a simple, interpretable detector that surpasses 99% accuracy, providing a transparent alternative to current black-box systems. Groundbreaking work for audio forensics and AI ethics!

📷 RenCon Live Concert - Thursday 7:30pm at KAIST Main Auditorium E15 RenCon (Expressive Rendering Contest) is an international challenge where researchers submit systems that can render expressive piano performances from symbolic scores. Today we're doing a live concert - the finalist systems will perform on a Disklavier, with a new surprise piece, and you get to vote for the winner! Thursday 9/25, 7:30pm. Free entry! More info: ren-con2025.vercel.app

🎸🥁 ISMIR 2025 Jam Session 🎹🎤 Get ready for one of ISMIR’s most beloved traditions — the Jam Session! 📅 Sep 24 (Wed), after the Conference Banquet 📍 Crystal Ballroom, ICC Hotel, Daejeon Bring your energy and join fellow ISMIRers for an unforgettable night of music, fun, and collaboration. Whether you sing, play, or just enjoy live music — you won’t want to miss it! 🎶 🎶 Available Instruments 2 guitars • 1 bass • drums 2 keyboards • acoustic piano 👉 Sign up to suggest songs & join the bands! Let’s make the 2025 Jam as legendary as ever! 🌟 #ismir2025 #jamsession #musicandfriends

🎶 BARAJI Concert at ISMIR 2025 🎶 Join us for a special evening of Korean traditional music with BARAJI (우리소리 바라지), one of the most renowned ensembles in the field. Rooted in shamanistic rituals (gut), BARAJI brings powerful performances that blend tradition with contemporary resonance. 📅 Sep 23, Tue, 18:30 📍KAIST Main Auditorium E15 👉 Concert Highlight Program Gayageum Sanjo (가야금 산조) Pansori: Simcheong-ga (심청가 中 심봉사 눈뜨는 대목) Daegeum Sanjo (대금 산조) Spirit Ensemble (씻김시나위) Muak (巫樂): Ensemble piece inspired by shamanistic ritual … and more, including prayers for happiness and well-being. ✨ This 70-minute concert will give ISMIR attendees a unique chance to experience the spiritual depth and cultural richness of Korean music — where sound becomes both expression and blessing. Don’t miss this rare performance at ISMIR 2025 in Daejeon, Korea! 🇰🇷

🇰🇷✨ K-Culture Night at ISMIR 2025 ✨🇰🇷 📅 September 23 (Tue), 19:30 📍 KAIST Main Auditorium E15 Join us for a festive evening celebrating Korea’s rich cultural heritage! 🎶🎭🍲 Don’t forget! Bring the cute & colorful pouch with the coins we gave you 🪙🪙🪙🪙 You’ll use these traditional K-coins to play games, enjoy drinks, and grab delicious food during K-Culture Night. Experience: 🎵 Learn to play traditional instruments (gayageum, haegeum, daegeum) 🎮 Try classic folk games like ddakji, jegi-chagi, tuho, and alkkagi 👘 Explore Korean culture hands-on: try on hanbok & learn Hangul 🍗🍜 Taste street foods like tteokbokki, dakgangjeong, gimbap, and more — plus traditional drinks! Collect coins by joining games & activities and redeem them for food and drinks. Don’t miss this unique chance to enjoy K-Culture Night with fellow ISMIR participants! 🔗 Learn more: ismir2025.ismir.net/program-kcultu… #ismir2025 #kculture #hallyu #koreantradition

🎶 ISMIR 2025 Music Program 🎶 Alongside world-class research, ISMIR 2025 presents a diverse Music Program that blends technology, tradition, and performance: 📅 Sep 22, Mon, 19:30 📍KAIST Main Auditorium E15 Mind Improvisation II — Real-time performance using brain signals (fNIRS) and Max/MSP, merging neuroscience with music improvisation. Aleatorica — A mosaic of melodies generated from large-scale music datasets, combining data visualization and sound art. Melody Slot Machine with RoboSax — AI-driven melody variations performed live by robotic saxophones. One, Two, Many — A collaboration between human flutists and AI, exploring interaction and aesthetic “preferences” in co-creation. ✨ From experimental AI collaborations to traditional-meets-digital expression, these performances highlight the creative frontier where music, technology, and research intersect. Explore the full details here: ismir2025.ismir.net/program-music

📍✨ ISMIR 2025 Campus Map & Venues ✨📍 Here’s your quick guide to the conference venues at KAIST: 📅 Sep 21 (Sun) – E11 Creative Learning B/D & E15 Auditorium Registration: E11 1F Lobby Tutorials: E11 101A, 102A, 103A 📅 Sep 22–25 (Mon–Thu) – E15 Auditorium Registration: E15 1F Lobby Main Conference Sessions • Oral Presentations: E15 Concert Hall • Poster Sessions: E15 Seminar Room 🔗 Full campus map: ismir2025.ismir.net/campus-map ⚠️ Important Notice Entrance Guide for E11: Due to construction, the entry marked in red is currently blocked. Please use the alternative entrances shown on the map. 🗺️ Check the images below for details and plan your route! #ismir2025 #conferenceguide #kaist

📅 ISMIR 2025 Full Schedule is Live! 📅 Plan your week in Daejeon, Korea with the full program of talks, tutorials, concerts, and special events. From inspiring keynotes to the BARAJI Korean Traditional Music Concert, and from industry meetups to the legendary banquet & jam session 🎶 👉 Explore the full schedule here: ismir2025.ismir.net/program 🗓️ Tip: You can also download the .ics file from the program page and add all sessions directly to your personal calendar! Get ready for an amazing week of music, research, and community at ISMIR 2025 💜

🎶🎹 Thank You to Our WiMIR Supporter: @SteinbergMedia ! 🎶 We’re delighted to recognize Steinberg as a WiMIR Supporter for ISMIR 2025, helping foster equity, creativity, and growth within the MIR community. Visit: ismir2025.ismir.net/meet-the-spons… #ismir2025 #wimir #womeninmusicinformationretrieval

🎼✨ Special Session at ISMIR 2025 ✨🎼 📅 September 24 (Wed), 17:30 How can we understand music and musical culture through perspectives beyond MIR? This Special Session brings together distinguished scholars from East Asia who explore music heritage through unconventional data sources — from historical gramophone recordings and ancient guqin tablature to cross-cultural datasets of song and speech. 👩‍🏫 Featured Speakers: Ying-fen Wang (National Taiwan University) – Sounding Taiwanese through Gramophone Recordings, 1895–1945 Yuto Ozaki (Keio University) – Exploring the evolutionary foundation of music through songs and speech across cultures Yu Hui (Nanjing Normal University) – Applying MIR to Chinese Guqin Tablature Research Join us for an inspiring session that bridges MIR, ethnomusicology, and cultural heritage! 🌏🎶 🔗 Learn more: ismir2025.ismir.net/program-specia… #ismir2025 #musicheritage #specialsession

🎶💡 Thank You to Our WiMIR Contributor: @Deezer ! 🎶 We’re excited to highlight Deezer as a WiMIR Contributor for ISMIR 2025, supporting diversity, equity, and innovation in music information retrieval. Visit: ismir2025.ismir.net/meet-the-spons… #ismir2025 #wimir #womeninmusicinformationretrieval

🎶🤖 Thank You to Our WiMIR Patron: @moises_ai ! We’re thrilled to recognize our WiMIR Patron Moises for playing a vital role in championing equity and growth in music information retrieval. Visit: ismir2025.ismir.net/meet-the-spons… #ismir2025 #wimir #womeninmusicinformationretrieval