MLMLMLM

What if listening happened through muscles instead of ears?

The Muscle-Listening Machine Learning Model for Live Music (MLMLMLM) is a novel deep generative model for muscle-sound machine translation. MLMLMLM is trained on a dataset of audio and EMG signals collected from my own body, during an artist residency at the Akademie der Künste, Berlin in July 2025.

VLA + MLMLMLM

MLMLMLM is situated within my music performance / composition / improvisation practice. I present MLMLMLM in live performance settings.

VLA + MLMLMLM is a performance piece featuring live viola and the Muscle-Listening Machine Learning Model for Live Music (MLMLMLM), a novel deep generative model for muscle-sound machine translation.

I interface with MLMLMLM through electromyographic sensors. MLMLMLM generates a sonic interpretation of live viola playing informed by the muscular bioelectricity of musical movement. The model ‘listens’ to the performance without ‘hearing’ sound.

With a human-centred approach to computing, VLA + MLMLMLM brings to light experiential dimensions of viola playing that are typically hidden from the audience. As such, we listen through emergent aesthetics of machine listening -- through muscles.

Publication:
Strauss, L., Thattai Ravikumar, P., Yee-King, M. ‘Cross-Modal Sig2Sig Machine Translation with Deep Generative Modeling for NIME Design’. International Conference on New Interfaces for Musical Expression, 2026. [accepted]