The MIT Music Know-how and Computation (MTC) Graduate Program — launched in fall 2024 as a collaboration between the Music and Theater Arts Part within the Faculty of Humanities, Arts, and Social Sciences (SHASS), and the Faculty of Engineering (SoE) — offered its inaugural MIT Music Know-how Analysis Showcase on Could 13. The occasion performed to a standing room-only home within the Edward and Joyce Linde Music Constructing’s Thomas Tull Live performance Corridor and featured various and charming analysis shows and music performances.
The celebratory event featured MTC’s first 5 enrollees (all of whom have been beforehand MIT undergraduates), alongside a number of PhD college students and school. Every scholar offered inspiring exemplars of suave engineering that mirrored the broader and burgeoning music expertise scene at MIT.
The 90-minute occasion exhibited a broad array of analysis tasks, together with a real-time visualization of what an AI co-improvising agent is about to play on a piano; a sound-art set up primarily based on noisy community communication; a hip-hop dance circle the place music is generated from dancing; and the usage of electroencephalogram (EEG) indicators to establish the musical tunes that our brains are imagining.
“A brand new area for exploration and insights”
An interaction of technical presentation with stay efficiency, the showcase started with remarks from SHASS Dean and professor of philosophy Agustín Rayo, SOE Dean and professor of chemical engineering Paula Hammond, and MTC Director and professor of the observe of music Eran Egozy.
Rayo started, “The purpose of this program is straightforward — for MIT to steer the world in music expertise principle and utility,” including “it’s not nearly making music with expertise; it’s additionally about working throughout disciplines to assist higher form the way forward for expression in an AI-driven world, all whereas reflecting MIT at its greatest.”
Rayo famous the graduate program was made attainable partly by the opening of the Edward and Joyce Linde Music Constructing in 2025, which offered new lecture rooms, studios, rehearsal areas, and a devoted music expertise lab. He additionally credited the MIT Schwarzman Faculty of Computing for its help for the graduate program.
Hammond adopted: “As these on this room already know, music and engineering share some frequent roots. Each depend on mathematical precision and are knowledgeable by outlined buildings, rhythms, and frequencies. Each demand onerous work and technical know-how, paired with inspiration and creativeness, to create one thing totally new. Given these congruities, it’s no shock that so many school, college students, and employees members throughout MIT are additionally achieved musicians and artists.”
She continued, “Our music program is a gem. Solely at MIT might we convey the highest technologists and the highest musicians collectively to create distinctive alternatives for collaboration. Right here we have now introduced collectively school and college students who establish strongly with each music and engineering to kind a brand new area for exploration and insights. It’s a powerful instance of the collaborative tradition that defines the Institute.”
Egozy referred to as the occasion a “harmonious hybrid of live performance and symposium,” and recollected, “it’s somewhat mind-boggling to see what our college students have achieved in only one brief and fast-paced 12 months. Whereas we initially debated the trade-offs between a one-year and a two-year grasp’s program, I believe this cohort actually confirmed us that we will make big strides in studying and analysis talents in a concentrated time frame.”
Pupil analysis on show
A type of college students is Claire Southard ’25, SM ’26, who developed a machine-learning mannequin used to establish musical notes hidden in EEG indicators.
Southard explains, “yearly, musicians are recognized with motion issues reminiscent of Parkinson’s illness and dystonia, or expertise accidents that forestall them from controlling their palms and our bodies within the methods required to play their devices. Due to this, too many musicians are pressured to cease doing what they love. My work explores one technique to assist such musicians carry out once more by translating the music they’re making an attempt to play straight from their mind exercise — bypassing the necessity for motor management altogether. To do that, I educated machine-learning fashions to foretell the music an individual is imagining from their mind exercise measured utilizing EEG, and lots of the predicted items have been discovered to be recognizable representations of what the consumer imagined. By designing a system that permits musicians to create music no matter their bodily talents, I hope this work helps convey a extra accessible future for music efficiency nearer to actuality.”
Earlier than becoming a member of MTC, Southard was initially unaware of the breadth, scope, and magnitude of what this system might supply for additional pursuing and realizing her pursuits. “The MIT Music Know-how and Computation Graduate Program taught me a lot concerning the prospects on the intersection of STEM and the humanities,” she says. “After I first began this system, I actually wasn’t positive what counted as ‘music expertise.’ By means of lessons, analysis, and conversations with school, visitor audio system, and friends, I realized the sphere was far broader and extra fascinating than I might have beforehand imagined.”
She continues, “coming from a background in neuro- and pc science, lots of my undergraduate tasks occurred totally on gadgets. However this program allowed me to come across extra hands-on experiences, from conducting audio recordings to constructing digital musical devices from scratch.”
One other MTC graduate, and scholar speaker on the 2026 SHASS Superior Diploma Ceremony, Mariano Salcedo ’25, SM ’26, offered a customized net utility permitting anybody to create distinctive emergent visuals which can be pushed by real-time streaming music. To perform this impact, Salcedo constructed algorithms that leverage the complicated visible habits of self-organized programs because the means towards an aesthetically synergetic finish.
In his Superior Diploma Ceremony oration, Salcedo expressed his gratitude and admiration for the passionate folks that he’s met not solely in MTC, however at MIT total. In an appropriately compassionate mode, he empathetically opined, “I believe what occasions like this name from us is to cleared the path in human and humane-centered expertise, which suggests we don’t solely simply ask what we will construct, however we additionally ask who’s it going to have an effect on, who is just not going to have an effect on? Who does it profit?”
Music expertise thriving at MIT
Affiliate Professor Anna Huang SM ’08 of MTA and the Division of Electrical Engineering and Pc Science (EECS, by SCC), a graduate of the MIT Media Lab, and one of many world’s main researchers in collaborative human-AI music-making, echoed each Southard and Salcedo’s sentiments by her keynote presentation, “In Search of Resonance in Human-AI Interplay.” A compelling and intimately conversational tackle, her speech emphasised the significance of centering the human musician in all that’s completed referring to AI, whereas additionally making efforts to incorporate all musics of the world in its discourse at each alternative.
With lots of her members of the family within the viewers, Huang mirrored, “I’ve the privilege of being in each MIT Music and EECS — an interdisciplinary, shared area. What does it imply to construct music expertise on this context? We’re surrounded by extraordinarily gifted musicians, so we take this co-design method: We work with these musicians, we go into the studio, and each week we attempt one thing. And the expertise grows with the artistic course of. We’re at all times making an attempt to push each of those ahead, and it’s at all times on the sting. It’s very, very rewarding. It’s the place I really feel most at dwelling.”
Huang additionally defined how this observe units the stage for a brand new Research in Music Know-how topic that she shall be co-teaching within the fall with lately appointed Professor of Theater Arts Grisha Coleman. Class 21M.369/569 (Tuning Consideration: Artistic Practices in Motion, Sound, and AI) proposes that the research of sound and motion practices can inform how we construct and envision computational programs, focusing significantly on our relationship to AIs. It is going to introduce college students to a variety of musical practices in improvisation and somatics by the use of motion-capture applied sciences, important interplay design, generative modeling, and algorithms for interpretability and studying by human suggestions.
All thought-about, the way forward for the MIT Music Know-how and Computation Graduate Program is brilliant. Egozy says MTC admitted 10 grasp’s college students for the 2026-27 tutorial 12 months from over 100 candidates. In contrast to this 12 months’s class, subsequent 12 months’s college students won’t solely embrace current MIT undergraduate alumni, but in addition new faces to campus.
“Widening the pool to graduates of different faculties and establishments will convey a unprecedented wealth of views and experiences to this system. Moreover, all three shared school between MTA and EECS — together with Mark Rau, Paris Smaragdis SM ’97, PhD ’01, and Huang — are inviting new Music Know-how PhD college students to their labs by the use of EECS,” Egozy says.
Embodying its mission, MTC is proving to be a vibrant, multidisciplinary program that draws many sorts of scholars with quite a lot of profession goals from wide-ranging backgrounds.
“Regardless of their variety, our college students all possess a central commonality,” Egozy says, “not only a shared love for music, but in addition a deep need to reinforce that keenness by the use of expertise in a really warmhearted, humanitarian manner.”
Checklist of tasks
Rachel Loh, Quanta Fellow in Music Know-how and Computation: “Visualizing the Inner State of Music Fashions for Reside Human-AI Improvisation”
Noble Harasha, Quanta Fellow in Music Know-how and Computation: “Modeling Subjectivity and Collective Sensory Notion as Noisy, Analog Communication in Suggestions-Pushed Networks”
Z Chen, Quanta Fellow in Music Know-how and Computation: “Generative Music as a Catalyst for Social Choreography”
Nithya Shikarpur: “The Shifting Drone: A Reside Improvisation within the Context of Hindustani Music with the Human Voice, Generative fashions, and Loops”
Mariano Salcedo, Alex Rigopulos (1992) Fellow in Music Know-how and Computation: “Neural Mobile Automata for Interactive Music Visualization”
Claire Southard, John Piscitello Fellow in Music Know-how and Computation: “Neural Decoding of Imagined Music”
Stephen Brade, Suwan Kim, Valerie Chen: “Whale, Cello (there?): A Musical Dialog between Cello and a Actual-time Diffusion Mannequin Educated on Whale Songs”
