MST
about — who I am and what I’m building
Pixel-art portrait of M. Stella Tavella
MST 2026

M. Stella
Tavella.

AI · Music · ML · Audio · Music Information Retrieval

Ciao! I’m a Principal AI Engineer at Musixmatch — building systems that understand music through lyrics, audio, and everything in between.

Research in agent orchestration, music information retrieval, and electronic music production.

10+ years in music tech. Founder of Music Tech Intelligence and co‑founder of the Italian Music Tech Community (ITMT). I’m also a music producer and DJ, experimenting with AI for music and live performance.

Now

Before

Education

research — peer-reviewed papers & patents

Peer-reviewed papers

2023 3 cit.

Exploiting Music Source Separation for Singing Voice Detection

F. Bonzi, M. Mancusi, S. Del Deo, P. Melucci, M.S. Tavella, L. Parisi, E. Rodolà

IEEE 33rd MLSP Workshop

(opens in a new tab)
2020 8 cit.

Butter Lyrics Over Hominy Grit — Comparing Audio and Psychology-Based Text Features in MIR Tasks

J. Kim, A.M. Demetriou, S. Manolios, M.S. Tavella, C.C.S. Liem

ISMIR 2020 — pp. 861–868

(opens in a new tab)
2019 21 cit.

Exploiting Synchronized Lyrics and Vocal Features for Music Emotion Detection

L. Parisi, S. Francia, S. Olivastri, M.S. Tavella

arXiv:1901.04831

(opens in a new tab)

Patents

2023 Granted

Method and System for Analyzing, Classifying, and Node-Ranking Content in Audio Tracks

L. Parisi, M. Paglia, A. Albano, P. Magnani, P. Melucci, M.S. Tavella

US Patent App. 17/869,053

(opens in a new tab)
2023 Granted

Systems and Methods for Artificial Intelligence Assistant Publishing

M.S. Tavella, L. Parisi, M. Bracci, G. Costantino, F. Delfino, P. Melucci

US Patent App. 18/337,905

(opens in a new tab)

projects — open-source tools for music & AI

macOS app Featured

aevum — live AI music performance, for macOS

A macOS app for live AI music performance, built on Magenta RealTime 2. Load songs, auto-extract musical loops, morph between them in real time, and control every generation parameter live with a MIDI controller.

stack
SwiftUI · Obj-C++ · Magenta RealTime 2
model
mrt2_small (230M) · mrt2_base (2.4B)
release
v0.1.0 · Apple Silicon · unsigned DMG
license
MIT (model weights CC-BY-4.0)
github (opens in a new tab) aevum.app (opens in a new tab) model (opens in a new tab)
Python Open Source

cocotagger — semantic music tagging, zero-shot

Tag audio with genre, mood, instruments, vocals, and texture — zero-shot via 768-dimensional MusicCoCa cosine similarity. 178 tags across 10 categories; runs entirely on a MacBook CPU, no GPU required.

stack
Python · TFLite · XNNPACK
model
MuLan → CoCa (MusicCoCa) · 44M YouTube tracks
tags
178 across genre / mood / instruments / vocals / texture / harmonic / tempo / era / production / energy
license
MIT
github (opens in a new tab) 10 GitHub stars (opens in a new tab)
Also open-sourced 4 repos
broski Visual browser automation for humans — drag-and-drop web scraping, testing, and monitoring workflows that drive Chromium live. (opens in a new tab) Modulr A modular music generation and synthesis framework. (opens in a new tab) musicnnCondVAE Conditional Variational Autoencoder for music generation with deep neural networks. (opens in a new tab) midi2img2vae MIDI → image conversion with a VAE for music generation and reconstruction. (opens in a new tab)

contact — collaborations, talks, or just hello