Publicaciones
Machine learning y procesamiento de señal para música: recuperación de información musical, detección de música generada por IA y síntesis neuronal de audio.
Algunas entradas de esta página solo están disponibles en inglés.
2026
How Much AI Is in This Track? Quantifying the Proportion of AI-Generated Stems in Hybrid Music Mixtures
Una CNN de regresión estima la proporción de energía IA de una mezcla con un MAE de 0,076 y R² = 0,85.
Binary detectors hit over 99% accuracy separating fully-AI from fully-human tracks, but producers mix an AI drum loop with a synthetic bassline and a human vocal. We reframe detection as regression over a continuous AI energy ratio: the fraction of a track's acoustic energy that comes from AI stems.
Binary detectors break down on such mixtures, and detectability varies sharply by instrument: drums and guitars leak strong neural-codec artifacts, vocals and bass far less.
Assessing AI-Generated Music Detection in Real-World Broadcast Monitoring
BAMM: 40 horas de música generada por IA y humana procedente de grabaciones reales de televisión.
Detectors that excel on clean audio degrade sharply in real broadcast conditions. We introduce BAMM and evaluate CNN detectors across three tiers of realism: clean foreground music, simulated TV broadcast, and genuine broadcast.
Broadcast-aware training improves robustness, but a substantial gap between laboratory results and practical deployment remains.
2022
From Words to Sound: Neural Audio Synthesis of Guitar Sounds with Timbral Descriptors
Un sintetizador de guitarra controlado por comandos de voz mediante descriptores tímbricos.
A deep-learning instrument that generates guitar sounds from vocal commands, extracting timbral descriptors from spoken input to steer a latent space that is otherwise high-dimensional and semantically opaque. Built within The Sound of AI Open Source Research initiative, with more than 200 contributors.