Keynote Speaker

Elizabeth Moody
2024-11-12 | 17:00 (America/Los_Angeles)

This speech explores the complex relationship between artificial intelligence and the music industry, tracing the evolution from early digital disruptions like Napster to today's AI-driven landscape. It examines how streaming platforms revolutionized music consumption and distribution, while also introducing new challenges such as streaming fraud. The speech delves into AI's multifaceted impact on music creation, production, and personalization, highlighting both its transformative potential and ethical concerns. The presentation also addresses controversial uses of voice AI technology and the legal and ethical considerations surrounding AI training data, including a fair use arguments and budding internal laws. Finally, we address proposed solutions, including the use of transparent attribution systems modeled after YouTube’s Content ID and policies for opt-in/out rights management. This keynote calls for a balanced approach, urging collaboration between artists, technologists, and policymakers to ensure that AI’s integration into music creation and distribution respects artistic integrity and promotes innovation.

Bio

ELIZABETH MOODY, partner and chair of Granderson Des Rochers, LLP's New Media Group, is a pioneer in the digital media world. Moody has been spearheading digital music and video initiatives since the post-Napster era, both as outside counsel, and as a business executive in-house at companies like YouTube and Pandora. Today, Moody remains positioned at the intersection of technology and music rights and continues to advise her technology and rightsholder clients toward new and innovative business models and licensing deals.

Moody is at the forefront of the developing issues and opportunities that AI presents to the music and entertainment industries. She counsels several prominent generative voice and audio AI companies, advises the non-profit Fairly Trained, which certifies AI companies who are training the data sets with fairly acquired, licensed or owned data, and Audioshake, an AI-based stem separation tool in use by record labels, movie studios, and entertainment companies today to ease production and marketing.

She is also keyed into the gaming and the web 3.0 world. She is partnerships counsel for the gaming company Roblox and also works closely with Wave XR, a virtual reality concerts start-up that works with artists to create unique live performances as avatar versions of themselves in imaginative digital landscapes. She developed and continues to grow Styngr’s efforts to power music in video games and online gaming experiences.

Along with gaming and the metaverse, she is passionate about the opportunities web 3.0 will bring to the music community and creators. She represents Audius, the blockchain-based music streaming service, in its efforts to help creators and their fans connect more authentically by embracing the opportunities offered through a decentralized network and Revelator, an all-in-one music platform providing digital distribution, analytics, and web 3.0 services to artists, record labels and publishers. She advises Copyright Delta, providing data connections to rights holders and AI tech platforms.

Moody is excited to bring opportunities to the music industry by forging deals with those in industries outside of music, including at the intersection of music and fitness. She represents connected fitness, yoga, pilates, mindfulness, cycling, and dance services to help them integrate music into their services. She has worked closely with Hydrow, the successful Peloton-style live reality-connected rowing experience, since its launch in 2019. She believes that VR plays an important role in fitness and works with Litesport and FitXR to ensure they have access to top-notch music experiences. She has also been working in the medical and wellness space exploring licensing structures to use music in the treatment of pain, dementia, and mental illness concerns through her work with MediMusic and her advisory participation on the board of Music Health.

Poster Sessions

Poster Session - 3

Nicholas Bryan

2024-11-12 | 09:45 (America/Los_Angeles)

In-person presentations:

Remote presentations:

Poster Session - 4

Dasaem Jeong

2024-11-12 | 15:30 (America/Los_Angeles)

In-person presentations:

Remote presentations:

Industry Session

Industry Session I

Brandi Frisbie, Minz Won

2024-11-12 | 11:00 (America/Los_Angeles)

This session will be the sponsor presentations.

  • MusicAI
  • Suno
  • Riffusion
  • Pro Sound Effects
  • Yamaha

Special Sessions

Online special session II

Martin Hartmann

2024-11-12 | 06:00 (America/Los_Angeles)

Join us for short presentations and informal conversations with invited researchers from the MIR community!

Martin Hartmann

Title: Music and Movement: exploring Social and Multimodal Dimensions of Rhythmic Entrainment.

Abstract: The talk addresses key challenges in the field of music and movement through two ongoing studies at the Centre of Excellence in Music, Mind, Body and Brain at the University of Jyväskylä. The first challenge explores rhythmic-social entrainment within the context of free dyadic dance. We present a study that examines the relationship between rhythmic-social entrainment and social as well as musical affiliation during adolescence, using markerless motion capture technology. Following a 2x2 factorial design, participants dance freely in dyads with a friend and with a stranger to music of their choice and to music selected by us. The second challenge focuses on the multimodality of rhythmic-social entrainment. We discuss a study that employs motion capture and surface electromyography to investigate the impact of visual cues and performed activities on acoustic features, physiological responses, and kinematic responses in choir singing. The goal is to understand how the visibility of other choir members and the performed activities (chat, homophony, polyphony, and musical improvisation) influence different types of individual and group responses. In addition to exploring the social aspects of rhythmic entrainment in dance and its multimodal nature in choir singing, we emphasize the extraction of musical features and individual and social acoustic and kinematic features. We also consider potential take-home messages from these studies for the music information retrieval community and beyond.

Kathleen Rose Agres Session II: 6 AM PT, 12th November, Online - ISMIR 2024

Title: Affective music generation for emotion regulation in listeners

Abstract: There has been a surge of interest in automatic music generation in recent years, particularly in affective music generation. Numerous systems now offer controllable AI-based affective music generation (AI-AMG), as highlighted in Dash & Agres (2024). While these systems have been developed for various applications—including soundtrack creation in gaming and virtual reality, co-creativity, and health and well-being—this talk focuses on the use of AI-AMG to support emotion regulation in listeners. One such system, AffectMachine (Agres, Dash, & Chua, 2023), is designed to generate affective music in real time, and is capable of composing in both classical and pop-music styles. Recent findings across several studies demonstrate AffectMachine’s efficacy in producing music perceived as emotional and capable of inducing emotions, as shown by subjective emotion ratings and physiological responses. This talk will explore the implications of systems like AffectMachine for supporting emotion self-regulation.

Kaustuv Kanti Ganguli Session II: 6 AM PT, 12th November, Online - ISMIR 2024

Title: Harmonic Convergence: Orchestrating the Synergy of Human Intuition and Machine Intelligence in Music

Abstract: In the rapidly evolving landscape of computational musicology, we stand at a fascinating crossroads where human perception intertwines with machine-driven analysis. This convergence offers unprecedented opportunities to unravel the complexities of musical structures, particularly in rich non-Eurogenetic traditions such as Indian art music. By harmonizing human cognition with artificial intelligence, we can decode the intricate artifacts of audio signal processing, revealing new dimensions in our understanding of music. This approach not only enhances our appreciation of musical nuances but also challenges us to rethink the boundaries between human creativity and computational analysis.

As we navigate this confluence, we must consider the profound implications for music education, composition, and appreciation. How can we leverage machine learning to augment human musical intuition? What new insights into musical cognition can emerge from this synthesis? By exploring these questions, we open doors to innovative pedagogical tools, more nuanced music recommendation systems, and perhaps even new forms of musical expression. The future of music analysis lies not in choosing between human expertise and artificial intelligence but in orchestrating a symphony where both play in perfect harmony, each enhancing the other's strengths and compensating for limitations.

Bio

Martin Hartmann is an Assistant Professor of Musicology at the University of Jyväskylä, where he works for the Centre of Excellence in Music, Mind, Body, and Brain and for the European Research Council project MUSICONNECT. His research encompasses music and movement, perception, information retrieval, and therapy. Currently, he specializes in the computational modeling of multimodal interactions in music and dance contexts. He is an executive group member of the Finnish Doctoral Network for Music Research and the local coordinator of the EU-funded FORTHEM Alliance Lab for Arts and Aesthetics in Contemporary Society. He led the project “Interaction in Music Therapy for Depression”, maintains the MoCap (Motion Capture) Toolbox for MATLAB, and holds editorial roles for the journals Music Perception and Psychology of Music.

Dr. Kat Agres is an Assistant Professor at the Yong Siew Toh Conservatory of Music at the National University of Singapore (NUS), and Founding Director of the Centre for Music and Health, the first dedicated research centre in Southeast Asia to spearhead evidence-based research leveraging the efficacy of music for health and well-being. Kat received her PhD in Cognitive Psychology from Cornell University and completed her postdoctoral fellowships in Music Cognition and Computational Creativity at the University of London. She also holds a bachelor's degree in Cello Performance and Psychology from Carnegie Mellon University. Kat’s research explores music interventions and technologies for healthcare and well-being, music perception and cognition, and computational creativity. She has received numerous grants to support her research in Singapore, the US, and UK. Kat has presented her research in over twenty countries around the world, and has also performed professionally as a cellist.

Dr. Kaustuv Kanti Ganguli is an Associate Professor of Artificial Intelligence at Zayed University and a Scholar at New York University Abu Dhabi Scholar, spearheading computational musicology and machine learning research. His innovative work bridges AI and music, focusing on Arabian Gulf and South Indian repertoires. Dr. Ganguli develops AI models that enhance music understanding, preservation, and education by combining engineering approaches with human cognition. A President's Gold Medal recipient and accomplished Hindustani vocal performer, his expertise spans machine learning, virtual reality, and audio processing. His groundbreaking projects include Raga/Makam characterization, multi-sensory perception, and crossmodal correspondence that collectively foster a deeper appreciation for diverse musical traditions through the lens of artificial intelligence. Kaustuv envisions blending humanistic and computational methods in a cross-disciplinary environment within a liberal arts framework, focusing on cutting-edge research and sustainable, innovative teaching.

Events

Online Q&A w/ volunteers

2024-11-12 | 08:00 (America/Los_Angeles)

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!

Online Q&A w/ volunteers

2024-11-12 | 20:00 (America/Los_Angeles)

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!

Mindfulness session

soundBrilliance

2024-11-12 | 11:45 (America/Los_Angeles)

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.

SoundBrilliance

Creative Practice

Creative Practice Session I

Cynthia Liem, Tomàs Peire

2024-11-12 | 13:15 (America/Los_Angeles)

Music information technology has the potential to transform creative and artistic practice. Many technologists working in music information retrieval also at least are music lovers (if not skilled players), and as such have strong commitment to having their tools and technologies being useful in practice. At the same time, are these technologists indeed sufficiently aligning to musical and creative practice? Are the needs and interests of relevant real-life music stakeholders (players, composers, producers, other types of practitioners) who never heard about ‘music information retrieval’ sufficiently identified and recognized in technological research and development?

As Creative Practice chairs, considering ISMIR 2024’s special focus on ‘Bridging Technology and Musical Creativity’, we want to stimulate more awareness of (and joint learning on) these questions. In order to do this, we wish to facilitate dialogues and collaborations on this topic between technologists and creatives. While several community members contributed ideas on which you can respond to collaborate (https://bit.ly/ismir24-creative-practice-ideas), at ISMIR 2024, we also will host two panels featuring invited guests who all are active on the bridges between technology and creative practice.

In today’s panel, we will host and have a conversation with:

  • Mark Goldstein - Percussionist, programmer, teacher, inventor; with an interest in the nexus of musical gesture, sound, and expression.
  • Michelle Alexander - Musician, Music Analyst & Mood Specialist at Pandora
  • Carlos Mosquera - Musician, Programmer, CEO at CM MEDIA LLC

Creative Practice Event at Riffusion

Cynthia Liem, Tomàs Peire, Riffusion

2024-11-12 | 18:00 (America/Los_Angeles)

Thank you to Riffusion for hosting this event!

Join us for an evening of music, drinks, and creative dialogue at the ISMIR Creative Practice x Riffusion SOCIAL on Tuesday, November 12th! Hosted at the Riffusion HQ and the audiophile lounge, Phonobar, this evening promises a great lineup of live performances and conversations bridging technology and musical creativity.

RSVP here: https://partiful.com/e/9HjldDxJTtSHXk2B5Mxc? . We have a few more spots than what capacity states now, but it will be important for people to bring their ISMIR badge.

Riffusion is a small team of musicians, engineers, and researchers building creative AI tools in San Francisco. We train foundation models for music generation, and envision Riffusion as a new musical instrument.

Riffusion