16th August, 2026. Recent lab member Nick Tong is presenting during DAFx at MIT next month. Nick and Tom’s paper is called “PAEDB: A synthetic primary-ambient dataset generation pipeline for automatic upmixing using deep neural networks”.
3rd June, 2026. The following lab members are presenting at the upcoming APME conference in Miami:
28th April, 2026. Lab member Jacey Schell has composed the score and designed sound for an interactive dome experience opening at the Frost Museum of Science Planetarium this weekend. Read more about the first Frost Museum x Frost School of Music collaboration here. Show times: this weekend only (Fri-Sun), 10:30 am, 1:30 pm, and 3:45 pm. Then 1:30 pm each day.
27th April, 2026. Lab member Sahan Wijewardane has had a paper entitled “A perceptual evaluation of various commercial models of music source separation, with a focus on model performance against non-traditional source material” accepted for AES Europe 2026, taking place in Copenhagen, Denmark, 26–28th May.
Lab associate Mafalda Nejmeddine, PhD student Chenyu Gao, and I have had a paper entitled “Patterns in 18th-century keyboard music: An approach to revealing Portuguese music identity” accepted for EuroMAC 2026, taking place in Barcelona, Spain, 7–10th September.
25th March, 2026. I presented a workshop on cocreating music with AI at AlgoRhythms 2026 at the Jacobs School of Music, Indiana University Bloomington, taking place 26–28th March.
16th November, 2025. Congratulations to our team “Auditory nerve” from the Frost School of Music, who received the 2nd highest public vote and finished 3rd overall in the 2025 International AI Song Contest, which took place at the Melkweg, Amsterdam.
The team consists of Mike Lundy, Jacey Schell, Brayton Russell, Asher Blum, Anish Ghosh, Raina Murnak, and Tom Collins. The main algorithmic contributions were from lab member Chenyu Gao’s VarGen model for generating variations on a given theme. We trained it on ~160 metal guitar tracks and then saw what came out when we prompted it with the theme of the carol “Silent night”…
2024. The team consisted of Amanda Pasler, Spencer Soule, Ryan Baker, Jack Reilly, Aditya Jeganath K., Eli Yaroch, Raina Murnak, and Tom Collins. Our song “Heart not found” finished 7th in the final, and the main algorithmic contributions were from Kits AI, MAIA Markov, and Synplant 2.
2023. We collaborated with Kemi Sulola and Harriet Raynor on a song called VTGO (Vertigo). The song finished 3rd in the 2023 AI Song Contest, and the main algorithmic contributions were from NoiseBandNet and CFE+P.
2022. We collaborated with NYC hip-hop artist G-Zone (aka Alex Gonzalez) and producer Jack McNeill on a song called “Nobody new”. SampleRNN and char-rnn provided the main algorithmic contributions.
2021. Lab PhD student Jemily Rime contributed the vocals to a song called “Circus”, produced by Liam Maloney, and with an awesome video created by Lynette Quek. WaveGAN, MAIA Markov, and TLDNE provided the main algorithmic contributions.
19th September, 2025. Taking place in Newman Recital Hall at the Frost School of Music, renowned pianist and composer Ayşedeniz Gökçin's show Classical Regenerated fused Chopin and Vivaldi with AI, reimagining classical music’s future.
Frost Senior Writer Jordan Levin has written a great article about the show, which you can check out here.
15th June, 2025. I'm delighted to announce the publication of a special collection in the journal Music & Science on the topic of “Explaining music with AI: Advancing the scientific understanding of music through computation”. This open-access collection has been guest-edited by David Meredith, Anja Volk and Tom Collins.
8th May, 2025. Congratulations to my University of York PhD student Chenyu Gao, who won an Open Research Prize for her work on Variation Transformer, and is also a finalist for the Humanities Research Centre Doctoral Fellowship Competition.
Congratluations also to CHAI project member Amari Stewart and lab member Nick Tong: Amari one Outstanding Music Engineering Undergraduate Student and Nick won the school-wide 2024-25 Outstanding Graduate Award at the Frost School of Music, University of Miami for his thesis work “UpmixAI: Automatic blind stereo-to-surround upmixing using music source separation deep neural networks”. Read more about the ceremony here.
14th April, 2025. The CHAI showcase took place on Saturday – a highlight of our U-LINK-funded project at University of Miami, which is called Concerts with Humans and Artificial Intelligence (CHAI).
Enjoy the promo video; checkout the YouTube recording.
25th February, 2025. The AI Summit of the Americas took place at University of Miami today. Tom co-chaired a panel called “Applications of AI in art” with Fedra Fateh, and panelists Fabiola Larios, and Stefon Harris.
19th February, 2025. In collaboration with Diliana Alexander of FilmGate Miami, and Kim Grinfeder of the School of Communication at University of Miami, Tom has contributed to a successful $100K bid to the Knight Foundation for a 2024 Knight New Work.
The project is called FLOW: A symphony of water and life. In the cypress forest, water whispers through ancient roots; On the verdant tapestry, its drowsy secrets are revealed; Murky carpets cradle tales retold, a silent symphony of holographic life.
FilmGate Miami, in collaboration with technical partner Moonshine (Taiwan), in partnership with the Frost School of Music and School of Communication at University of Miami, and in partnership with presenting venue the Phillip and Patricia Frost Museum of Science (Frost Science), will create an original and groundbreaking dome and LED experience to premiere at the 12th edition of the FilmGate Interactive Media Festival in December 2025.
Students at Frost will benefit from the opportunity to receive some training in immersive sound, generative AI for visuals and music, and other attendant technologies.
26th November, 2024. Congratulations to lab member Jemily Rime, whose paper “Interviewing ChatGPT-generated personas to inform design decisions” won best paper award at the Interational Conference on Computer-Human Interaction Research and Applications (CHIRA).
6th November, 2024. Audio collage at its best.
10th November, 2024. The International Society for Music Information Retrieval (ISMIR) Conference is taking place November 10–14 in San Francisco.
The lab has two papers at the conference this year:
29th November, 2023. VTGO (Vertigo), a collaboration with Kemi Sulola and Harriet Raynor, is out today! See here to listen to it on your platform of choice.
We're proud to say the song finished 3rd in the 2023 AI Song Contest!
19th July, 2023. Lab members Chenyu Gao and Tom Collins are presenting at the HCI International Conference and the associated Workshop on Interactive Technologies for Analysing and Visualising Musical Structure in Copenhagen, beginning Sunday 23rd July.
Chenyu's contribution is about interactive pendular graphs, which can be explored here.
18th July, 2023. Lab PhD student
Adrián Barahona-Ríos
has been working on sound effect modelling and synthesis. The new
model, indicated in the diagram above and called
NoiseBandNet,
has some exciting creative applications. For example, once trained on a
sound like this metal impact:
we can drive the timbral world of metal impact with the loudness
curve extracted from another sound, such as this beat box clip:
resulting in an interesting hybrid:
In addition to the music-creative possibilities indicated above, we anticipate applications in game audio and XR, where until now it has been labour-intensive to generate scene-driven alterations to sound effects.
14th April, 2023. Congratulations to former lab member Zongyu Yin, who has won the Computer Science Dept.'s Best PhD Thesis Prize for 2022, for his work New evaluation methods for automatic music generation.
10th April, 2020. "It's doing what I hoped it would do, which is what I believe AI will do for musicians, which is to push us to the next level of our own creativity" (Imogen Heap, Grammy Award-winning musican and technologist on working with music generation algorithms built in the lab).
12 April, 2021. Here are some fun, educational interfaces for kids to explore music technology. We have found some of these interfaces engage kids as young as two years old. For kids aged four and above, up to you whether to explore side-by-side with them, or say farewell to your device and let them have at it...
Learning JavaScript is a good place to start. I've put some demos below to get you excited about wanting to do this! Read more...
Here are some examples of dynamic web-based music interfaces that have been developed in the lab, using packages built on the Web Audio API. For pedagogical purposes, we have used mostly basic JavaScript, left comments in the code, and avoided optimizations like minifying. If you make JSFiddles, CodePens, or your own standalone interfaces based directly or indirectly on what you find below, please feel free to share them with us to enhance the pedagogical experience!
To rework/extend the demos, you'll need to understand how to program in HTML, CSS, JavaScript, PHP, and Node.js, with the most important of these being JavaScript. Read more...
In the interests of closing the gender pay gap, my salary as an Associate Professor at a private institution is $129K.
We like hearing from people who are interested in contributing to the work of the lab. At the moment, we're particularly interested in hearing from people with software engineering expertise who are looking for more autonomy and to learn some research skills.
Feel free to get in touch if you fit any of the categories below.
Familiarity with Node.js and SQLite or another database solution. Experience with client-side syntax/library such as Handlebars, React, or Vue. Ideal candidate has experience with building single-page web applications from API to UI/X with authorization and access control.
First-author publications and/or evidence of writing productivity appropriate to level. Experience as a music scholar, a computer scientist, a cognitive scientist, or some combination of the three. Demonstration of willingness to work on and optimize time-consuming tasks such as data collection and analysis, and music data curation.
Interest in music, computer science, cognitive science, or some combination of the three. Has looked at the demos and attempted to rework/extend at least one of them.
Both in the lab and with collaborators across the globe, we apply the scientific method to explore...
This is a team of researchers that we hope will develop in exciting ways over the next decades – even beyond the current PI's retirement! If you are interested in working with us, you are welcome to get in touch to discuss opportunities. We're happy to try to support face-to-face research visits and/or distributed collaborations.
Here's the team, present and past, in pseudo-random order...
I hope you enjoyed visiting this site.
Feel free to get in touch (tom.collins@miami.edu) if you have any
questions or suggestions.
The code above was written by Tom Collins and others as specified (e.g., toward the bottom of each demo interface). Reuse of the code is welcomed, and governed by the GNU General Public License Version 3 or later.