Reactive, human-like systems that support musicians during practice and performance.

AIM is a music technology research group at . Some of our projects are supported by a National Science Foundation grant.

See our research Join the team

Projects

Active research

Five projects spanning automatic transcription, real-time accompaniment, and embodied performance.

View all research

Fall 2024 – present

Automatic Music Transcription

Streamlining audio-to-MIDI transcription for musicians and educators, with applications in isolating sounds in noisy environments.

Learn more

Fall 2023 – present

Evaluator

An app that helps musicians practice more effectively, using computer vision and YOLO localization to track posture, with spectrogram analysis and multi-modal transformers to identify mistakes.

Learn more

Fall 2023 – present

Companion

An app that plays along with a human player during a chamber music piece and actively responds to their playing habits and voice commands.

Learn more

Spring 2022 – present

Mus2Vid

A real-time art project that uses diffusion models to generate video depictions in response to classical music, with recurrent and transformer networks estimating emotion and genre.

Learn more

Spring 2024 – present

Robot Cello

Using reinforcement learning to teach a robot arm to play cello. The project partners with the Purdue Envision Center for motion-capture training data.

Learn more

Publications

Recent work

Peer-reviewed publications from the lab.

AAAI 2025

Detecting Music Performance Errors with Transformers

Benjamin Shiue-Hal Chou, Purvish Jajal, Nicholas John Eliopoulos, Tim Nadolsky, Cheng-Yun Yang, Nikita Ravi, James C. Davis, Kristen Yeon-Ji Yun, Yung-Hsiang Lu

AAAI · 2025 · Vol. 39, Issue 22 · pp. 23687–23695

▸BibTeX

BibTeX

@article{Chou2025,
  author  = {Chou, Benjamin Shiue-Hal and Jajal, Purvish and Eliopoulos, Nicholas John and Nadolsky, Tim and Yang, Cheng-Yun and Ravi, Nikita and Davis, James C. and Yun, Kristen Yeon-Ji and Lu, Yung-Hsiang},
  title   = {Detecting Music Performance Errors with Transformers},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume  = {39},
  number  = {22},
  pages   = {23687--23695},
  year    = {2025},
  doi     = {10.1609/aaai.v39i22.34539}
}

News

Recent events

Workshops and competitions from the lab.

January 01 – April 30, 2025

2025 Transcription Competition

Challenge participants to create the best transcription model for classical music. 17 teams submitted; results published on the leaderboard.

Learn more

March 3, 2025

AI for Music — AAAI 2025 Workshop

Discover the latest advancements in AI for music at AAAI 2025. Six invited speakers, ten accepted papers.

Learn more

June 30, 2025

AI for Music — ICME 2025 Workshop

Join us for an exciting workshop where we'll explore the dynamic intersection of artificial intelligence and music. Five invited speakers + technical program committee.

Learn more

Research areas

Where our projects sit in the field

Our projects often span most or all of these areas.

Generative Audio and DSP

How can Companion utilize machine learning and filtering to resynthesize string instrument articulations on-the-fly?

Beat Detection and Tempo Tracking

What are the most effective methods for Companion, Evaluator, and Mus2Vid to follow a musician's playing in reference to a score, and play along to match?

Emotion and Perception

How can Mus2Vid analyze emotion of classical music in real-time and utilize it to generate real-time video accompaniments?

Music Classification / Information Retrieval

What musical features extracted from various media — such as tempo, key, genre, notes — are useful to music performance technology, and how can we extract such features?

Human-Computer Interaction

How can our apps be designed in ways that are human-like and natural for humans to interact with?

User Studies + Deployments

How can we ensure that our users actually utilize and enjoy the apps we develop?

Team

A multidisciplinary group

Our 15 researchers come from engineering, music, science, liberal arts, design, and management.

Meet the team

Outreach

How AIM connects with the community

Vertically Integrated Project

AIM has an associated Vertically Integrated Project, which enables research experiences for Purdue undergraduates.

Learn more

Multidisciplinary Research

Music technology is a field with very multidisciplinary problems and solutions. We draw from Music, Electrical and Computer Engineering, Computer Science, Technology, Art, Design, and Management.

User Studies

AIM actively runs user studies on the tools that are developed to ensure that users can figure out how to use them and enjoy them.

Presentations / Concerts

AIM members have given speeches, presentations, and concerts about and using AIM technology around the world.