BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ICMC HAMBURG 2026 - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:ICMC HAMBURG 2026
X-ORIGINAL-URL:http://icmc2026.ligeti-zentrum.de
X-WR-CALDESC:Events for ICMC HAMBURG 2026
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Amsterdam
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20270328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20271031T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Amsterdam:20260515T090000
DTEND;TZID=Europe/Amsterdam:20260515T103000
DTSTAMP:20260610T111940
CREATED:20260415T142419Z
LAST-MODIFIED:20260511T161723Z
UID:10000099-1778835600-1778841000@icmc2026.ligeti-zentrum.de
SUMMARY:Paper Session 10b: Interactive Media II
DESCRIPTION:Session Chair: Felipe Otondo\n\nPaper abstracts\nFabian Ostermann: “BbMuse: A Blackboard-Driven Framework for Real-Time Interactive Music”\nInteractive music systems are frequently built as ad hoc multi-agent architectures with custom communication protocols and project-specific execution models\, while recent machine-learning approaches often encapsulate behavior in monolithic\, computationally expensive black boxes. This paper revisits blackboard architectures for real-time interactive music generation and argues that composition and musical interaction can be modeled as distributed decision-making processes operating on shared musical state. We introduce BbMuse (BlackBoard MUSic Engine)\, an open-source\, platform-independent Python framework that implements a dataflow-oriented blackboard variant inspired by real-time robotics. System state is encoded as typed representations on a global blackboard\, while modules explicitly declare required and provided information\, enabling automatic scheduling via topological sorting. As a result\, system development becomes incremental and module-focused\, since no inter-module dependencies must be specified. Further\, the framework supports concurrent execution and demonstrates that real-time performance is possible with Python using native-library acceleration. We provide a growing collection of example projects\, discuss diverse use cases and outline future features for learning-based module replacement as well as a GUI editor. \nEun Ji Oh\, Jun Woo Beck and Alexandria Smith: “The Singing Skin: An Audience-Centered Biofeedback System for Musical Interaction Based on Galvanic Skin Response”\nMusic can evoke measurable physiological responses\, yet these responses have been predominantly explored from the performer’s perspective in interactive and biofeedback-based music systems. In contrast\, the sonification of audience physiology remains relatively underexplored in live music contexts. We present The Singing Skin\, a real-time\, audience-centered biofeedback system for live performance that integrates listeners’ physiological responses into musical control. The system measures galvanic skin response (GSR) and uses the phasic component of the GSR signal as an index of moment-to-moment audience engagement. This phasic GSR–based control signal is normalized and mapped to the rhythmic subdivision of a monophonic lead line generated by a wavetable synthesizer. Rather than directly modifying tempo or pitch\, the control signal modulates the cutoff rate of a low-pass filter\, producing an indirect pacing effect that influences perceived musical drive and energy. The system is demonstrated in a live performance setting involving a violinist and a listener equipped with GSR sensors. This work contributes a novel approach to audience-inclusive musical interaction by extending audience physiology as an active control source in live music\nperformance.\nPenelope Bekiari and Anastasia Georgaki: “Hyponoia: An Affective Computing System for Augmented Musical Performance — A Case Study”\nThis paper investigates how EEG-driven biofeedback systems influence performability and listening strategies in contemporary electroacoustic performance. We introduce Hyponoia (Hyper-Observational Neuro-Oscillation Interactive Agency)\, a real-time interactive system that translates performers’ neurophysiological activity into state-based compositional behaviours. Unlike conventional EEG-based musical interfaces that map signals to discrete parameters\, Hyponoia operates at the level of musical processes\, structuring sonic form through inferred neuro-affective states. The system integrates EEG and heart-rate data within a closed biophysical feedback loop\, in which performers’ internal cognitive and affective states dynamically interact with the evolving sonic environment. A comparative case study was conducted with expert and non-expert musicians performing in open-form electroacoustic contexts. We hypothesise that performers with sound-based expertise exhibit distinct patterns of neural engagement and interaction with the system. Results indicate that expert performers demonstrate richer theta activity\, more coherent alpha modulation\, and greater neural variability\, associated with enhanced internal auditory imagery and anticipatory listening. In contrast\, non-expert performers exhibit more constrained neural responses and reduced sensitivity to spectromorphological change. These findings suggest that performability in biofeedback-driven systems depends less on instrumental technique than on listening literacy and embodied sonic awareness. Rather than acting as an autonomous agent\, the system functions as a responsive mediator that amplifies differences in perceptual and cognitive engagement\, contributing to an emerging performance aesthetic grounded in physiological feedback and real-time interaction. \n 
URL:http://icmc2026.ligeti-zentrum.de/event/paper-session-10b-interactive-media/
LOCATION:Hamburg University of Technology\, Building H\, Ditze Hörsaal (H 0.16)\, Am Schwarzenberg-Campus 5\, Hamburg\, 21073\, Germany
CATEGORIES:15-05,Paper Session,Session
ORGANIZER;CN="ICMC HAMBURG 2026":MAILTO:info@icmc2026.ligeti-zentrum.de
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Amsterdam:20260514T123000
DTEND;TZID=Europe/Amsterdam:20260514T133000
DTSTAMP:20260610T111940
CREATED:20260423T164652Z
LAST-MODIFIED:20260508T135636Z
UID:10000229-1778761800-1778765400@icmc2026.ligeti-zentrum.de
SUMMARY:ICMA General Meeting
DESCRIPTION:TBA
URL:http://icmc2026.ligeti-zentrum.de/event/icma-general-meeting/
LOCATION:Hamburg University of Technology\, Building H\, Ditze Hörsaal (H 0.16)\, Am Schwarzenberg-Campus 5\, Hamburg\, 21073\, Germany
CATEGORIES:14-05,ICMA
ORGANIZER;CN="ICMC HAMBURG 2026":MAILTO:info@icmc2026.ligeti-zentrum.de
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Amsterdam:20260514T090000
DTEND;TZID=Europe/Amsterdam:20260514T103000
DTSTAMP:20260610T111940
CREATED:20260422T134949Z
LAST-MODIFIED:20260511T160941Z
UID:10000220-1778749200-1778754600@icmc2026.ligeti-zentrum.de
SUMMARY:Paper Session 7b: Interactive Media I
DESCRIPTION:Session Chair: Mara Helmuth\n  \nPaper abstracts\nAdriano C. Monteiro and Rafaela B. Pires: “Exploring DIY Cassava-Starch Bioplastic Interfaces with EFT-Based Touch Sensing in an Interactive Sound Installation”\nThis paper reports the design\, implementation\, and preliminary validation of a tangible interface that combines electrical field tomography (EFT)\, support vector machines (SVM)\, and cassava-starch bioplastics for an interactive sound installation. The system addresses two main challenges: 1) creating low-cost\, large-area touch surfaces with flexible geometries\, and 2) integrating bio-degradable materials into electronic interfaces while preserving sufficient electrical and mechanical stability for real-time performance. It consists of bioplastic interfaces\, custom hardware for multiplexed current injection and voltage measurement\, and a software pipeline for signal conditioning and SVM-based touch classification. Results show that the system can reliably distinguish a vocabulary of touch gestures on irregular bioplastic objects\, while also revealing limitations related to long-term stability\, calibration\, and object-specific training. Finally\, the paper discusses its integration into De/Re:Generation\, a sound installation where bioplastic sculptures operate both as scenographic elements and as interactive surfaces within a vibro-acoustic environment inspired by the cicada life cycle.\nGuanjun Qin\, Yunxuan Jia and Neal Farwell: “Reimagining Athletic Gesture: Transforming Basketball Sound into Narrative Electroacoustic Music”\nThis paper presents FMVP\, an electroacoustic fixed-media composition that transforms the sounds of basketball into a narrative of doubt\, struggle\, and redemption. Built entirely from field recordings captured on an indoor court\, the work reimagines sport as a metaphor for resilience and creative endurance. Through granular time-stretching\, spectral transformation\, dynamic filtering\, and spatial motion\, physical gestures such as dribbling\, sliding\, and impact are translated into evolving sonic textures and large-scale form. Inspired by the career arc of NBA player Stephen Curry\, the composition explores how kinetic rhythms can be reshaped into emotional trajectories\, aligning with the conference theme of Innovation\, Translation\, Participation. Methodologically\, the project sits within artistic research\, using composition as a mode of inquiry into the relationship between embodied action and sound narrative. The paper discusses the conceptual framework\, sound-design process\, and structural strategies underpinning FMVP\, arguing that everyday athletic environments offer rich material for electroacoustic storytelling and for rethinking how listeners participate in narratives constructed purely through sound.\nSitong Wu and Jinshuo Feng: “Gestalt: A Symbiotic Framework for Real-Time Collaboration  between Performers and Mass Audiences”\nThis paper presents Gestalt\, a real-time co-creative audiovisual performance system for professional performers and large-scale audiences. To address participation barriers\, interaction latency\, and unequal creative agency in Networked Music Performance (NMP)\, Gestalt adopts a browser-based heterogeneous architecture: performers retain structural control via MediaPipe-based motion capture\, while 50 –200 audience members participate through a mobile web multi-touch interface. Centered on a mechanism termed “Translation\,” the system performs a dual reconstruction. On the audio side\, an activity-weighted aggregation algorithm transforms large volumes of discrete gestures into coherent musical textures. On the visual side\, audience touch inputs are streamed in real time to a physics-driven WebGL particle stage\, translating collective crowd activity into ordered audiovisual forms. Technically\, the web frontend connects to a Max/MSP audio engine via OSC (Open Sound Control)\, and to the visual stage via WebSocket. Benchmark tests and pilot workshops examine how the architecture can preserve performer-led form while enabling audience aesthetic agency. Gestalt is released as an open-source platform for future interactive media creation. \n 
URL:http://icmc2026.ligeti-zentrum.de/event/paper-session-7b-interactive-media/
LOCATION:Hamburg University of Technology\, Building H\, Ditze Hörsaal (H 0.16)\, Am Schwarzenberg-Campus 5\, Hamburg\, 21073\, Germany
CATEGORIES:14-05,Paper Session,Session
ORGANIZER;CN="ICMC HAMBURG 2026":MAILTO:info@icmc2026.ligeti-zentrum.de
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Amsterdam:20260513T160000
DTEND;TZID=Europe/Amsterdam:20260513T180000
DTSTAMP:20260610T111940
CREATED:20260421T130933Z
LAST-MODIFIED:20260507T093524Z
UID:10000171-1778688000-1778695200@icmc2026.ligeti-zentrum.de
SUMMARY:Special Panel: Clarence Barlow
DESCRIPTION:Panelists\nFabian Czolbe \nBernd Härpfer \nJohn Chowning \nAnne Wellmer \nModeration: Georg Hajdu \n  \nAbout the panelists & their perspectives\nFabian Czolbe\, Julian Rohrhuber and Bernd Härpfer : “Amplifying Participation. The digital Barlow Archive (dBA) as an Approach to the Recording of a Digital Computer Music Legacy”\nThe archiving of computer music presents specific challenges that arise from the process-oriented\, software-based\, and technologically contingent nature of digital compositional practices. Digital artifacts such as source code\, algorithmically generated data\, and custom compositional tools encode not only musical outcomes but also procedural knowledge that is often implicit and difficult to formalize. This paper presents the Digital Barlow Archive (dBA)\, which may be taken as a case study for addressing these challenges through a translational and participatory approach to archiving computer music.\nThe born-digital legacy of Clarence Barlow (1945–2023) is open-ended and comprises heterogeneous materials. For doing justice to this openness and diversity\, the dBA adheres to existing archival standards while extending them to account for computer-music-specific objects and workflows. Thereby\, an object/event framework is employed to translate non-linear and iterative compositional processes into structured metadata representations that remain interoperable with institutional and international archival infrastructures. At the same time\, the framework acknowledges the limits of formalization and preserves interpretative openness.\nExtending the old idea of computing as an amplification of the intellect\, this paper argues that such archival methods do not only passively conserve material\, but need to translate and amplify the possibility of participation: they actively shape access\, interpretation\, and creative reuse of digital musical materials. Archiving should be conducted as an epistemic practice that mediates between technological history\, compositional knowledge\, and the contemporary computer music community.  \n  \nBernd Härpfer: “From pioneer to role model – a tribute to Clarence Barlow’s legacy to computer music and the ICMC” (invited)\nFor over five decades\, Clarence Barlow (1945-2023) has made significant contributions to contemporary music and\, in particular\, to computer music. He is recognised worldwide as a composer\, interdisciplinary researcher\, author\, software developer and professor. Another defining characteristic was his talent for bringing people together\, networking the scene and demonstrating great organisational stamina. A key milestone in this regard was the organisation and hosting of the 14th ICMC – the first time the event was held in Germany – in Cologne in 1988.  \n   \nAnne Wellmer: “On the Poetry of Indigestibility ξ”\n\nClarence Barlow was teaching at Sonology in the mid-nineties. A microtonal organ almost completely filled the room (BEA7) where he was teaching his course On Musiquantics. Clarence was a story teller. He would come up with hilarious and inspiring solutions for problems that seemingly could not be overcome… \nAbout the panelist\nanne wellmer | nonlinear is a composer performer based in The Hague. During her vocal studies at the Conservatory in Amsterdam in the early 1990s she discovered electronic music through workshops by Trevor Wishart and Joel Ryan and was introduced to the analog studio where noone except two composition students and her were working at the time. She decided to leave Schubert behind and moved on to study Sonology at the Royal Conservatory in The Hague. This is where she met Clarence Barlow. For a while STEIM became her second home. Shortly before September 11 she moved to Connecticut to study composition with Alvin Lucier. Back in the Netherlands\, she worked on the disclore of Dick Raaijmakers’ archive\, and updated the Sonology database so it could be included in the EMDoku (the International Documentation of Electroacoustic Music). Her work includes music theater pieces\, sound walks\, radio art\, fixed media and live performance. Since 2017 she has been teaching courses on experimental music within Art and Media at the Berlin University of the Arts.\nanne wellmer is a member of the society for nontrivial pursuits in Berlin and founding member of the nomadic collective new emergences. Recent collaborations include “the annes” with anne la berge\, “the octopussies” with Kristin Norderval and “triple A” with Alberto de Campo and Ariane Jeßulat.\nMore about anne welmer | nonlinear here: www.nonlinear.demon.nl \n  \nRaphael Radna: “Tombeau de Barleau: An Interactive Ludic–Algorithmic Composition in Honor of Clarence Barlow”\nTombeau de Barleau is an interactive\, generative\, and audiovisual composition dedicated to the pioneering computer-music composer Clarence Barlow (1945–2023)\, a teacher of the author. In this work\, two performers play a Pong-style video game in which collisions between the ball and a portrait of Barlow play a MIDI-controlled piano. The performers affect this process only indirectly\, as the gameplay itself governs musical parameters including harmony\, density\, rhythm\, dynamics\, and tempo. As a result\, the work balances novelty and determinism: while its musical surface varies across performances\, its underlying algorithmic structure provides a stable form. \nTombeau de Barleau adopts several elements of Barlow’s compositional style\, including rigorously formalized algorithmic processes\, unconventional uses of piano automata\, translations between visual and musical domains\, and playful or outlandish premises. It also applies some of his theoretical contributions\, namely his methods for quantifying the consonance of harmonic intervals (harmonicity) and priority of metrical pulses (indispensability). This paper describes the design and implementation of Tombeau de Barleau and reflects on its function as an homage to one of algorithmic music’s most inventive and influential figures.  \n  \nJohn Chowning: “Algorithmic compositions at Bell Telephone Laboratories in the 1960s” (invited)\nIn the domain of computer music\, the first algorithmic compositions were at Bell Telephone Laboratories (BTL) in the 1960s.  Max Mathews and colleagues\, encouraged and joined by John R. Pierce\, Director of Research\, experimented with Mathews and Joan Miller’s Music III and IV programs\, with notable results. While Mathews and Pierce did not claim to be composers\, they had musical instincts\, and the ideas in their algorithmic compositions were brilliant\, though often cartoonish sounding. \nIn my presentation\, I will present and explain a selection of works by composers including Mathews\, Pierce\, James Tenney\, and Jean-Claude Risset. \nAbout the panelist\nJohn Chowning was born in Salem\, New Jersey in 1934\, spending his school years in Wilmington\, Delaware. Following military service and four years at Wittenberg University in Ohio\, he studied composition in Paris with Nadia Boulanger. He received the doctorate in composition (DMA) from Stanford University in 1966\, where he studied with Leland Smith. \nIn 1964\, with the help of Max Mathews of Bell Telephone Laboratories and David Poole of Stanford University\, he set up a computer music program using the computer system of Stanford’s Artificial Intelligence Laboratory. Beginning the same year he began the research that led to the first generalized surround sound localization algorithm. In trying to comprehend the distance cue\, Chowning discovered the frequency modulation synthesis (FM) algorithm in 1967. This breakthrough in the synthesis of timbres allowed a very simple yet elegant way of creating and controlling time-varying spectra. Inspired by the perceptual research of Jean-Claude Risset\, he worked toward turning this discovery into a system of musical importance\, using it extensively in his compositions. In 1973 Stanford University licensed the FM synthesis patent to Yamaha in Japan\, leading to the most successful synthesis engine in the history of electronic musical instruments. Interview about FM synthesis Jun 17\, 2015\, Barcelona\, https://rwm.macba.cat/en/sonia/sonia-212-john-chowning \nHe taught computer-sound synthesis and composition at Stanford University’s Department of Music. In 1974\, with John Grey\, James (Andy) Moorer\, Loren Rush and Leland Smith\, he founded the Center for Computer Research in Music and Acoustics (CCRMA)\, which remains one of the leading centers for computer music and related research. Although he retired in 1996\, he has remained in contact with CCRMA activities. In 2019\, he initiated with an international team\, a long-term project to recreate\, by computer modeling\, the acoustics of the Chauvet Cave in France as they were when the exqusite 36\,000-32\,000-year-old wall paintings were created. \nChowning was elected to the American Academy of Arts and Sciences in 1988 and awarded the Honorary Doctor of Music by Wittenberg University in 1990. The French Ministre de la Culture awarded him the Diplôme d’Officier dans l’Ordre des Arts et Lettres in 1995. He was given the Doctorat Honoris Causa in 2002 by the Université de la Méditerranée\, by Queen’s University in 2010\, Hamburg University of Music and Drama in 2016 and Laureate of the Giga-Hertz-Award in 2013. \n 
URL:http://icmc2026.ligeti-zentrum.de/event/special-panel-clarence-barlow/
LOCATION:Hamburg University of Technology\, Building H\, Ditze Hörsaal (H 0.16)\, Am Schwarzenberg-Campus 5\, Hamburg\, 21073\, Germany
CATEGORIES:13-05,Panel
ORGANIZER;CN="ICMC HAMBURG 2026":MAILTO:info@icmc2026.ligeti-zentrum.de
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Amsterdam:20260513T110000
DTEND;TZID=Europe/Amsterdam:20260513T123000
DTSTAMP:20260610T111940
CREATED:20260415T134319Z
LAST-MODIFIED:20260511T160523Z
UID:10000084-1778670000-1778675400@icmc2026.ligeti-zentrum.de
SUMMARY:Paper Session 6b: AI & Machine Learning
DESCRIPTION:Session Chair: Nicola L. Hein\n  \nPaper abstracts\nGiovanni Roma and Alba Francesca Battista: “Supervised Memory: How Machines Can Preserve What We Cannot Hold”\nThis paper presents an AI framework for preserving electroacoustic works threatened by technological obsolescence and vanishing performance knowledge. Through supervised annotation as “composition of comprehension\,” we transform machine learning into active interpretation rather than passive archiving. Our approach employs a two-level vocabulary system distinguishing universal from composer-specific notational elements\, enabling systematic knowledge transfer across diverse repertoires. We ground the framework in one implemented reconstruction—Jonathan Harvey’s Ricercare una melodia from incomplete documentation—and outline two further experimental\nfronts: analyzing context-dependent notation in Stockhausen’s Solo\, and exploring annotation possibilities in Boulez’s spatial coordinates. The methodology treats annotation not as neutral transcription but as interpretive translation\, where each label embeds aesthetic decisions and performance practice. Harvey’s implementation revealed how editorial simplification between 1984 and 2003 editions created cascading performance challenges\, validating our recovery of embedded procedural knowledge. The framework progresses from mechanical reproduction through systematic reading to conscious reactivation\, establishing foundations for computational preservation while acknowledging fundamental limits. We argue that effective preservation requires not static archives but living traditions maintained by transparent\, contestable machine interpretations. This positions AI-based complements as participants in musical preservation rather than mere repositories\, preserving both structural relationships and the reasoning patterns that animate them. \nAbhirup Saha\, Hans-Ulrich Berendes\, Meinard Müller\, and Ben Maman: “Snapping Matters: Context-Aware Onset Refinement for Automatic Music Transcription”\nPrecise note-level annotations are critical for training automatic music transcription (AMT) systems\, in particular note-onset labels\, which form a core component of many recent AMT systems. However\, high-quality annotations for real-world recordings are scarce. Sequence-level score–audio alignment methods such as dynamic time warping provide only coarse correspondence\, making a local refinement step necessary. This refinement step\, known as snapping\, adjusts aligned score onsets using peaks in a neural onset posteriorgram and often determines whether weakly aligned score–audio pairs become usable training data at all. Despite its practical importance\, snapping is typically treated as a simple post-processing heuristic and implemented with greedy local decisions. We present a systematic analysis of snapping strategies for training instrument-agnostic transcribers\, demonstrating that snapping is essential for learning from weakly aligned data. Building on this\, we formulate snapping as a per-pitch assignment problem and solve it via bipartite graph matching\, yielding context-aware onset decisions under overlapping refinement windows and uncertain initial alignments. Extensive cross-dataset experiments across piano\, chamber\, and orchestral recordings show improved onset alignment and transcription accuracy over greedy snapping\, with gains increasing for wider snapping windows and coarser initial alignments. Qualitative examples are provided on our project page: https://abhirupsaha8.github.io \nYu Foon Darin Chau and Andrew Horner: “Classical Music Mashup System and Compatibility Heuristics”\nWe investigate symbolic classical music mashups and introduce a retrieval-based pipeline for generating them. Unlike audio-domain mashups\, symbolic mashups offer perfect voice isolation and allow for post-generation reinterpretation of tempo\, dynamics\, and instrumentation. While prior work in audio mashups emphasises harmony\, rhythm\, and balance\, symbolic mashups in classical repertoires remain underexplored and lack clear compatibility heuristics. To this end\, we conduct controlled listening tests on classical music excerpts to isolate factors shaping perceived compatibility. Results indicate effective mashups should respect the recognizability of motivic materials\, underlying cadential logic\, and be presented polyphonically. We designed a symbolic mashup pipeline for classical piano music around these findings that maximises pairwise piece compatibility. We discuss implications and limitations for algorithmic composition\, pedagogical tools\, and future extensions to broader styles\, longer forms\, and richer evaluative methodologies. \n 
URL:http://icmc2026.ligeti-zentrum.de/event/paper-session-6b-ai-machine-learning/
LOCATION:Hamburg University of Technology\, Building H\, Ditze Hörsaal (H 0.16)\, Am Schwarzenberg-Campus 5\, Hamburg\, 21073\, Germany
CATEGORIES:13-05,Paper Session,Session
ORGANIZER;CN="ICMC HAMBURG 2026":MAILTO:info@icmc2026.ligeti-zentrum.de
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Amsterdam:20260513T090000
DTEND;TZID=Europe/Amsterdam:20260513T103000
DTSTAMP:20260610T111940
CREATED:20260415T133500Z
LAST-MODIFIED:20260511T155501Z
UID:10000082-1778662800-1778668200@icmc2026.ligeti-zentrum.de
SUMMARY:Paper Session 5b: AI\, Machine Learning & Pedagogy
DESCRIPTION:Session Chair: Rodrigo Cadiz\n\nPaper Abstracts\nJeff Kaiser and Gregory Taylor: “Building Loopers: A Pedagogical Framework for Teaching Creative Software Design Through Iterative Tool Construction in Max\, gen~\, and RNBO”\nThis paper introduces the ideas behind our open-access project “Building Live Loopers in Max.”1 The project presents a hybrid pedagogical and technical framework in which students learn signal processing concepts by constructing live-looping tools in Max\, gen~\, and RNBO. By engaging with buffer operations\, timing structures\, playback manipulation\, and parameter mapping\, students develop technical fluency and musical understanding simultaneously. We introduce a sequence of modular\, step-by-step looper designs\, a color-coded instructional method for visualizing patcher development\, and a cross-environment workflow that reinforces transferable pro-\ngramming habits. Our coursework is designed to be sufficiently open-ended that students\, while grounded in familiar musical contexts\, are encouraged to exercise curiosity and explore creative directions beyond the methods presented. Drawing on Dehaene’s work on curiosity and Eagle-\nman’s writing on relevance\, the design aims to engage intrinsic motivation and support students in forming novel connections and actively experimenting with musical ideas. This approach positions looper construction as a bridge between creative music-making and computational thinking\, supporting both performance and pedagogical outcomes. \nNicolas Brochec and Jean-Louis Giavitto: “Automatic Following of Flute Playing Techniques for Real-Time Mixed Music: A Case Study with Antescofo and ipt~”\nThis paper investigates how real-time recognition of instrumental playing techniques can extend automatic score following beyond the limits of pitch-based alignment. While systems such as Antescofo provide robust and largely plug-and-play score following\, their listening model is primarily designed for stable\, pitched events aligned with a fixed symbolic score. This makes them difficult to adapt to extended techniques\, unpitched sounds\, and musical forms involving partial improvisation or open notation. To address these limitations\, we explore a hybrid approach that combines multiple listening machines with complementary capabilities and allows dynamic switching between them during performance according to the musical context. Specifically\, we integrate Antescofo with ipt˜\, a real-time playing technique recognition system based on lightweight machine learning models. We focus on the integration of real-time instrumental playing technique recognition as a means to enrich the listening process and support technique-aware navigation of the score. We evaluate this approach on the case of extended flute techniques\, assessing both the feasibility of technique aware following and the trade-off between system generality and performance. Results suggest that learning-based listening modules provide a practical compromise: they improve\nrobustness for specific techniques while preserving much of the plug-and-play character supporting multiple works and performers. The results highlight a promising balance between generality\, specificity\, and performative robustness.\nColton Arnold\, Zhaohan Cheng and Ajay Kapur: “AI Framework for Dynamic Robotic Instrument Calibration”\nThis paper presents a data-driven calibration framework for robotic musical instruments based on a hybrid ensemble model that combines K-nearest neighbors (KNN) and a multi-layer perceptron (MLP). KNN anchors predictions to recorded acoustic measurements\, while the MLP enables nonlinear generalization and smooth interpolation across the instrument’s playable range. A distance-dependent blending strategy integrates the two models\, improving consistency across sparse and dense data. The proposed approach produces stable and repeatable calibration estimates for both pitched and non-pitched instruments\, outperforming standalone models across a range of sampling conditions. This work establishes a scalable foundation for automated calibration in robotic musical systems.\n 
URL:http://icmc2026.ligeti-zentrum.de/event/paper-session-5b-ai-machine-learning-pedagogy/
LOCATION:Hamburg University of Technology\, Building H\, Ditze Hörsaal (H 0.16)\, Am Schwarzenberg-Campus 5\, Hamburg\, 21073\, Germany
CATEGORIES:13-05,Paper Session,Session
ORGANIZER;CN="ICMC HAMBURG 2026":MAILTO:info@icmc2026.ligeti-zentrum.de
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Amsterdam:20260512T110000
DTEND;TZID=Europe/Amsterdam:20260512T123000
DTSTAMP:20260610T111940
CREATED:20260415T133949Z
LAST-MODIFIED:20260511T155410Z
UID:10000129-1778583600-1778589000@icmc2026.ligeti-zentrum.de
SUMMARY:Paper Session 4b: Physiological and Physical Foundations of Creative Systems II
DESCRIPTION:Session Chair: Simon Linke\n  \nPaper Abstracts\nRolf Bader and Simon Linke: “Impulse Pattern Formulation (IPF) Brain and Larynx Model as a Co-Musician Sound Synthesis Method”\nA sound synthesis method is proposed as a variation of the Impulse Pattern Formulation (IPF) sound synthesis introduced before\, now combining an IPF Brain model previously proposed\, driven by a simple IPF of brain input stimulation and acting on a larynx IPF for vocalization. The resulting sounds produce timbre\, rhythm\, articulation\, and large-scale form with a single algorithm reminding on complex articulated vocalization of living being. A systematic investigation of the Brain IPF with the input IPF shows many kinds of articulations for converging\, bifurcating\, and chaotic IPF input\, but only the chaotic input has a high likeliness to end in a distinct sound. By varying the amount of excitatory vs. inhibitory neuron relations of the IPF Brain model\, realistic relations found in humans are found to have a wider distribution of articulatory possibilities. Varying the adaptation strength of the Brain IPF\, distinct sounds can often only be produced by certain values\, where some sounds can only be produced by no or a strong adaptation but not for medium adaptation strength\nvalues. Overall\, the relation between the Brain IPF output and its parameters are too complex to easily predict its output\, making this synthesis method a co-composer for a musician or composer displaying its ’own will’\, so a unique sound synthesis co-musician method. \nTim Ziemer: “Mel-Frequency Cepstral Coefficients and Recording Studio Features for the Analysis of Producer-Driven Music”\nIn music information retrieval\, Mel frequency cepstral co-efficients are a ubiquitous set of audio analysis features that has proven its value for practical tasks\, like automatic genre recognition or playlist generation. However\, in the recording studio practice\, a very different set of audio analysis tools is consulted. In this study\, we utilize audio analysis tools from the recording studio for house and techno music analysis\, and compare its discriminative power and its interpretability with Mel frequency cepstral coefficients. In a quantitative style classification task\, recording studio features perform slightly worse than Mel frequency cepstral coefficients. However\, they are much more explanatory when it comes to exploring differences between US and German music. The set of features is a promising tool for the research of producer-driven music.\nSimon Linke\, Rolf Bader and Robert Mores: “Designing responsive rhythms utilizing the Impulse Pattern Formulation (IPF)”\nImpulse Pattern Formulation (IPF) is an analytical modeling approach for synergetic systems motivated by research on musical instruments. It describes the nonlinear coupling of system components as the interaction between individually propagating\, exponentially damped impulse trains. Due to this general approach\, the IPF has been successfully applied to topics other than musical instruments and is hypothesized to be capable of modeling the entire process of musical perception and performance in the future. This work investigates how the IPF can be applied as a compositional tool that reproduces fundamental musical behavior by modelling the synchronization of musicians to an external rhythm. The derived model is systematically examined by analyzing its behavior when coupled to numerically designed and carefully controlled rhythmical beat sequences. Thus\, in the future\, the IPF model can be applied\, e.g.\, to replace drum machines and click tracks with more musical and creative solutions. \n 
URL:http://icmc2026.ligeti-zentrum.de/event/paper-session-4b-physiological-and-physical-foundations-of-creative-systems-ii/
LOCATION:Hamburg University of Technology\, Building H\, Ditze Hörsaal (H 0.16)\, Am Schwarzenberg-Campus 5\, Hamburg\, 21073\, Germany
CATEGORIES:12-05,Paper Session,Session
ORGANIZER;CN="ICMC HAMBURG 2026":MAILTO:info@icmc2026.ligeti-zentrum.de
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Amsterdam:20260512T090000
DTEND;TZID=Europe/Amsterdam:20260512T223000
DTSTAMP:20260610T111940
CREATED:20260415T132257Z
LAST-MODIFIED:20260511T155028Z
UID:10000083-1778576400-1778625000@icmc2026.ligeti-zentrum.de
SUMMARY:Paper Session 3b: Physiological and Physical Foundations of Creative Systems I
DESCRIPTION:Session Chair: Tony de Ritis\n  \nPaper abstracts\nAmir Abbas Orouji\, Ayoub Banoushi and Gilberto Bernardes: “Vibrational Analysis of Traditional Persian Kamanche Sound Box: Experimental and Computational Investigation of Structural Modifications”\nThe kamanche\, a bowed spike fiddle central to Persian classical music\, features a spherical sound box covered with stretched animal skin and is played vertically on the performer’s lap. Despite acoustic similarities to the violin\, comprehensive research on kamanche acoustics remains limited. This study investigates the acoustic contribution of the sound box to resonance characteristics and tonal quality of the closed-back kamanche\, the most prevalent contemporary variant. The research combines COMSOL Multiphysics vibration simulation with experimental validation through impulse response frequency measurements. Investigated modifications include upper and lower hemisphere thickness variations and sound hole area reduction. Results demonstrate that upper hemisphere changes\, while preserving internal air volume\, substantially affect fundamental resonance patterns\, corroborating traditional luthier observations. This study also suggests that the vibration modes 4\,5\, and especially 7 might be good candidates for maximum contribution to the overall amplifica-\ntion of the string’s resonance and the overall sound of the instrument. \nNikolaus Knop: “Ponticello: An Interactive Conducting System for Mixed Music Performance”\nIn composed music that combines acoustic instruments with electronic processing or fixed media\, synchronizing acoustic and electronic layers remains a persistent challenge. The use of click tracks\, while technically effective\, significantly restricts the performers’ freedom to expressively shape musical time. This paper presents Ponticello\, a system that addresses the synchronization problem by inferring the ensemble’s tempo from a video stream of the conductor in real-time. Instead of the ensemble being beholden to a fixed digital click track\, the computer follows the flexible pulse indicated by the conductor\, which already functions as a shared temporal reference for the human performers. Although the idea of interactive conducting systems is not new —it has been researched since the 1970s — research has largely focused on applications that simulate instrumental performances based on MIDI scores\, which limits their applicability to the performance of mixed music. To support a broad range of compositional strategies for mixed music\, Ponticello instead models the electronic part as a timeline of temporally extended\, electronic processes whose playback tempo is continuously controlled by the conductor. The system has proven sufficiently reliable and accurate in rehearsal and concert settings across multiple conductors.\nLucas Ong\, Ruby Crocker and George Fazekas: “Emotion-Based Film Music Retrieval with Handcrafted and Deep Models”\nFilm music powerfully conveys emotion\, yet computational methods for retrieving film tracks that match a target emotional state remain underexplored. This paper presents two approaches for emotion-based film music retrieval using Valence–Arousal (V–A) representations. The models are evaluated on the FME-24 dataset\, which provides time-aligned participant-annotated V–A ratings for film music excerpts. The first approach applies k-Means to handcrafted audio features\, while the second uses a VaDE model with contrastive learning to align audio and V–A embeddings. Results show that both methods capture emotion-related structure\, with the deep model enabling more flexible\, fine-grained selection. \n 
URL:http://icmc2026.ligeti-zentrum.de/event/paper-session-3b-physiological-physical-foundations-creative-solutions/
LOCATION:Hamburg University of Technology\, Building H\, Ditze Hörsaal (H 0.16)\, Am Schwarzenberg-Campus 5\, Hamburg\, 21073\, Germany
CATEGORIES:12-05,Paper Session,Session
ORGANIZER;CN="ICMC HAMBURG 2026":MAILTO:info@icmc2026.ligeti-zentrum.de
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Amsterdam:20260511T110000
DTEND;TZID=Europe/Amsterdam:20260511T123000
DTSTAMP:20260610T111940
CREATED:20260422T142327Z
LAST-MODIFIED:20260511T154743Z
UID:10000222-1778497200-1778502600@icmc2026.ligeti-zentrum.de
SUMMARY:Paper Session 2b: AI & Music
DESCRIPTION:Session Chair: Paulo Chagas\nPaper abstracts\nHiroshi Yamato\, OrbitScore: “A Domain-Specific Language for Polymetric Live Coding Based on Multilayered Temporal Structures”\nThis paper presents OrbitScore\, a domain-specific language (DSL) for live coding polymetric rhythm patterns based on the theory of Multilayered Temporal Structures (MLTS). While existing live coding languages such as TidalCycles and Sonic Pi provide rich pattern manipulation capabilities including polyrhythmic support\, OrbitScore offers an intuitive syntax where the beat(n by m) notation directly\nmaps to the theoretical 4:(n/4) framework\, enabling each sequence to maintain its own meter and allowing performers to create intricate polyrhythmic textures in real-time. The system integrates with SuperCollider for low-latency audio synthesis and provides a declarative\, method-chaining syntax designed for live performance. We describe the theoretical foundation\, DSL design\, implementation architecture\, and demonstrate the system’s capabilities through a live coding performance. Our contribution lies in bridging the gap between the theoretical framework of Multilayered Temporal Structures and practical live coding tools\, making polymetric expressions accessible to performers. \nPiero Poli: “Dancing Cabiria: An hyper-environment study through corpus-based techniques”\nThis paper introduces the concept of hyper-environment — an additional spatial layer superimposed on the choreographic space\, where physical movement becomes a means\nof navigating and activating pre-analyzed sound materials. The work examines Dancing Cabiria\, a reenactment in four scenes from Giovanni Pastrone’s silent film Cabiria (1914)\, as a case study to explore performative hyper-environments that employ corpus-based synthesis techniques within a virtual reality framework. Through the use of motion-tracking suits\, four choreographies are performed\, each one by four dancers whose movements are translated into sound via audio corpora distributed throughout the virtual space surrounding each performer. Each choreography outlines different uses and configurations of this hyper-environment\, and allow for the discussion of compositional and instrumental issues such as the scale and density of the corpora\, the relationship that emerges between movements width\, corpus dimensions\, and virtual space volume\, and the role of real-time feedback in the design of hybrid instruments for performers. \nMinami Kojima\, Takayuki Itoh and Rafael Ramirez: “Factor Analysis of Similarity in the Same Orchestral Piece”\nThere have been conventional research comparing multiple performances of the same classical music piece\, where many of them primarily discussed the similarity between performances but rarely delved into why those performances are similar. Furthermore\, conventional similarity analysis has dealt with the similarity of single features in classical music\, such as timbre\, tempo\, and loudness. However\, since actual audiences perceive these features compounded without separating them\, relying solely on single features is insufficient to fully represent musical style. To overcome this challenge\, our study uses a deep learning model (VGGish\, specialized in audio feature extraction) that captures high-level timbral and textural features\, in addition to acoustic features (timbre\, loudness\, tempo)\, targeting the same orchestral piece. Subsequently\, based on those features\, we define five grouping criteria: (1) same orchestra\, (2) same conductor\, (3) same country of orchestra\, (4) same nationality of conductor\, and (5) same teacher of the conductor. We then evaluate the clustering performance for each criterion. A group exhibiting high clustering performance suggests mutual similarity among the performances within that group\, leading us to conclude that the corresponding criterion represents a major factor influencing performance style. The results in this paper show that conductor identity consistently yields\nthe strongest clustering for tempo-related features\, while orchestra identity dominates timbral similarity in specific movements. We demonstrate that metadata-driven factors explain similarity beyond purely perceptual or affective similarity measures. \n 
URL:http://icmc2026.ligeti-zentrum.de/event/paper-session-2b-ai-music/
LOCATION:Hamburg University of Technology\, Building H\, Ditze Hörsaal (H 0.16)\, Am Schwarzenberg-Campus 5\, Hamburg\, 21073\, Germany
CATEGORIES:11-05,Paper Session,Session
ORGANIZER;CN="ICMC HAMBURG 2026":MAILTO:info@icmc2026.ligeti-zentrum.de
END:VEVENT
END:VCALENDAR