Searcharxiv⌕ Search

arXiv subjects

Mauricio Zuluaga

Publications and source records attributed to Mauricio Zuluaga.

5 recordsLinked to original sources

Live Music Models

We introduce a new class of generative models for music called live music models that produce a continuous stream of music in real-time with synchronized user control. We release Magenta RealTime, an open-weights live music model that can be steered using text or audio prompts to control acoustic style. On automatic metrics of music quality, Magenta RealTime outperforms other open-weights music generation models, despite using fewer parameters and offering first-of-its-kind live generation capabilities. We also release Lyria RealTime, an API-based model with extended controls, offering access to our most powerful model with wide prompt coverage. These models demonstrate a new paradigm for AI-assisted music creation that emphasizes human-in-the-loop interaction for live music performance.

cs.SD↗

Fréchet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms

We propose the Fréchet Audio Distance (FAD), a novel, reference-free evaluation metric for music enhancement algorithms. We demonstrate how typical evaluation metrics for speech enhancement and blind source separation can fail to accurately measure the perceived effect of a wide variety of distortions. As an alternative, we propose adapting the Fréchet Inception Distance (FID) metric used to evaluate generative image models to the audio domain. FAD is validated using a wide variety of artificial distortions and is compared to the signal based metrics signal to distortion ratio (SDR), cosine distance and magnitude L2 distance. We show that, with a correlation coefficient of 0.52, FAD correlates more closely with human perception than either SDR, cosine distance or magnitude L2 distance, with correlation coefficients of 0.39, -0.15 and -0.01 respectively.

eess.AS↗

Random walks systems with finite lifetime on $ \bbZ $

We consider a non-homogeneous random walks system on $\bbZ$ in which each active particle performs a nearest neighbor random walk and activates all inactive particles it encounters up to a total amount of $L$ jumps. We present necessary and sufficient conditions for the process to survive, which means that an infinite number of random walks become activated.

math.PR↗

The cone percolation on $\bbT_d$

We study a rumour model from a percolation theory and branching process point of view. The existence of a giant component is related to the event where the rumour spreads out trough an infinite number of individuals. We present sharp lower and upper bounds for the probability of that event, according to the distribution of the random variables that defines the radius of influence of each individual.

math.PR↗

Rumour Processes on N

We study four discrete time stochastic systems on $\bbN$ modeling processes of rumour spreading. The involved individuals can either have an active or a passive role, speaking up or asking for the rumour. The appetite in spreading or hearing the rumour is represented by a set of random variables whose distributions may depend on the individuals. Our goal is to understand - based on those random variables distribution - whether the probability of having an infinite set of individuals knowing the rumour is positive or not.

math.PR↗