← All student projects · Bela Gem projects

An intelligent instrument in one box: IMPSY on Bela Gem

Combine sensing, an AI model, and sound synthesis in one low-latency Bela Gem instrument.

Level: Honours, Masters
Prerequisites: C++ and some embedded or audio programming (e.g., COMP2300 or COMP4350/COMP8350). Some machine learning background is helpful.

IMPSY currently runs on a Raspberry Pi connected to external MIDI instruments. Bela Gem could combine sensing, the AI model, and sound synthesis in one low-latency device. IMPSY’s models are small (two 64-unit LSTM layers and a mixture density output), so real-time inference on Bela Gem should be well within reach. In this project you’ll write an MDRNN inference engine in C++ using weights exported from IMPSY’s models, and verify it step by step against IMPSY’s reference test vectors.

• One semester: a C++ MDRNN runtime that passes IMPSY’s reference tests, plus latency and timing benchmarks against the Raspberry Pi version.
• Two semesters or Master: connect the model to Bela’s sensor inputs and audio synthesis to build a playable standalone intelligent instrument, and evaluate it in performance.

Tags: #embedded #Bela #C++ #real-time #IMPSY

How to apply

Contact Charles Martin with your CV, your unofficial transcript (if you are an ANU student), and a brief statement (200 words) explaining how you would approach this project. Before applying, read the Join page and our project expectations.