In-person presentations:

• Scoring Time Intervals Using Non-Hierarchical Transformer for Automatic Piano Transcription - Yujia Yan (University of Rochester)*, Zhiyao Duan (University of Rochester)
• CADENZA: A Generative Framework for Expressive Musical Ideas and Variations - Julian Lenz (Lemonaide ), Anirudh Mani (Lemonaide)*
• Looking for Tactus in All the Wrong Places: Statistical Inference of Metric Alignment in Rap Flow - Nathaniel Condit-Schultz (Georgia Institute of Technology)*
• Exploring GPT's Ability as a Judge in Music Understanding - Kun Fang (McGill University)*, Ziyu Wang (NYU Shanghai), Gus Xia (New York University Shanghai), Ichiro Fujinaga (McGill University)
• Towards Assessing Data Replication in Music Generation with Music Similarity Metrics on Raw Audio - Roser Batlle-Roca (Universitat Pompeu Fabra)*, Wei-Hsiang Liao (Sony Group Corporation), Xavier Serra (Universitat Pompeu Fabra ), Yuki Mitsufuji (Sony AI), Emilia Gomez (Joint Research Centre, European Commission & Universitat Pompeu Fabra)
• Generating Sample-Based Musical Instruments Using Neural Audio Codec Language Models - Shahan Nercessian (Native Instruments)*, Johannes Imort (Native Instruments), Ninon Devis (Native Instruments), Frederik Blang (Native Instruments)
• HIERARCHICAL GENERATIVE MODELING OF THE MELODIC VOICE IN HINDUSTANI CLASSICAL MUSIC - Nithya Nadig Shikarpur (Mila, University of Montreal)*, Krishna Maneesha Dendukuri (Mila), Yusong Wu (Mila, University of Montreal), Antoine CAILLON (IRCAM), Cheng-Zhi Anna Huang (Google Brain)
• SymPAC: Scalable Symbolic Music Generation With Prompts And Constraints - Haonan Chen (Bytedance Inc.)*, Jordan B. L. Smith (TikTok), Janne Spijkervet (University of Amsterdam), Ju-Chiang Wang (ByteDance), Pei Zou (Bytedance Inc.), Bochen Li (University of Rochester), Qiuqiang Kong (Byte Dance), Xingjian Du (University of Rochester)
• Unsupervised Composable Representations for Audio - Giovanni Bindi (IRCAM)*, Philippe Esling
• CCOM-HuQin: An Annotated Multimodal Chinese Fiddle Performance Dataset - Yu Zhang, Ziya Zhou*, Xiaobing Li, Feng Yu, Maosong Sun
• Lyrically Speaking: Exploring the Link Between Lyrical Emotions, Themes and Depression Risk - Pavani B Chowdary (International Institute of Information Technology, Hyderabad)*, Bhavyajeet Singh (International Institute of Information Technology, Hyderabad ), Rajat Agarwal (International Institute of Information Technology), Vinoo Alluri (IIIT - Hyderabad)
• A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems - Karn N Watcharasupat (Georgia Institute of Technology)*, Alexander Lerch (Georgia Institute of Technology)
• Towards Musically Informed Evaluation of Piano Transcription Models - Patricia Hu (Johannes Kepler University)*, Lukáš Samuel Marták (Johannes Kepler University Linz), Carlos Eduardo Cancino-Chacón (Johannes Kepler University Linz), Gerhard Widmer (Johannes Kepler University)
• Using Item Response Theory to Aggregate Music Annotation Results of Multiple Annotators - Tomoyasu Nakano (National Institute of Advanced Industrial Science and Technology (AIST))*, Masataka Goto (National Institute of Advanced Industrial Science and Technology (AIST))
• Just Label the Repeats for In-The-Wild Audio-to-Score Alignment - Irmak Bukey (Carnegie Mellon University)*, Michael Feffer (Carnegie Mellon University), Chris Donahue (CMU)
• Investigating Time-Line-Based Music Traditions with Field Recordings: A Case Study of Candomblé Bell Patterns - Lucas S Maia (Universidade Federal do Rio de Janeiro)*, Richa Namballa (New York University), Martín Rocamora (Universidad de la República), Magdalena Fuentes (New York University), Carlos Guedes (NYU Abu Dhabi)
• PiJAMA: Piano Jazz with Automatic MIDI Annotations - Drew Edwards*, Simon Dixon, Emmanouil Benetos

Remote presentations:

• In-depth performance analysis of the ADTOF-based algorithm for automatic drum transcription - Mickael Zehren (Umeå University)*

Having issues with Zoom or Slack? Need help navigating the conference program or materials? Virtual volunteers will be available to meet with you and answer any questions you may have!

The unconference is a set of impromptu sessions/discussions on MIR topics of greatest interest.
During a first plenary, participants vote on their preferred topics, then join a 30-minute discussion group on this topic, after which they summarize their discussions in a second plenary, vote on new topics, and repeat the process with new groups. Topics do not need to be technical (example: what does MIR stands for ? do we need open-review ? does gen-ai cares about copyright ? how many multi-head do I need in my encoder ?). This is an informal and informative opportunity to get to know peers and colleagues from around the world.

Having issues with Zoom or Slack? Need help navigating the conference program or materials? Virtual volunteers will be available to meet with you and answer any questions you may have!

soundBrilliance is an innovative digital health company using enhanced music, psychology, and measurement techniques to create tools and exercises which empower people to better self-manage fundamental health – emotional balance, fitness, quality sleep and pain control. The experiences presented in the ISMIR 2024 Mindfulness sessions are designed to help guide you into a deeper sense of Calm. All visuals are naturally produced and captured, with no AI intervention.

The LBD session is a forum for presenting prototype systems, initial concepts, and early results that are not yet fully matured but hold significance for the Music Information Retrieval (MIR) community. This joint session with MIREX includes poster presentations and live demos from both LBD and MIREX submissions.

The LBD session is a forum for presenting prototype systems, initial concepts, and early results that are not yet fully matured but hold significance for the Music Information Retrieval (MIR) community. This joint session with MIREX includes poster presentations and live demos from both LBD and MIREX submissions.

The LBD session is a forum for presenting prototype systems, initial concepts, and early results that are not yet fully matured but hold significance for the Music Information Retrieval (MIR) community. This joint session with MIREX includes poster presentations and live demos from both LBD and MIREX submissions.