Search Results for author:
Found 8 papers, 5 papers with code
Timbre latent space: exploration and creative aspects
Recent studies show the ability of unsupervised models to learn invertible audio representations using Auto-Encoders.
Neural Granular Sound Synthesis
In this setting the learned grain space is invertible, meaning that we can continuously synthesize sound when traversing its dimensions.
Ultra-light deep MIR by trimming lottery tickets
We show that our proposal can remove up to 90% of the model parameters without loss of accuracy, leading to ultra-light deep MIR models.
Diet deep generative audio models with structured lottery
This hypothesis states that extremely efficient small sub-networks exist in deep models and would provide higher accuracy than larger models if trained in isolation.
Vector-Quantized Timbre Representation
Although its definition is usually elusive, it can be seen from a signal processing viewpoint as all the spectral features that are perceived independently from pitch and loudness.
Assisted Sound Sample Generation with Musical Conditioning in Adversarial Auto-Encoders
Its training data subsets can directly be visualized in the 3D latent representation.
Modulated Variational auto-Encoders for many-to-many musical timbre transfer
We define timbre transfer as applying parts of the auditory properties of a musical instrument onto another.
Sound Audio and Speech Processing
Generative timbre spaces: regularizing variational auto-encoders with perceptual metrics
Based on this, we introduce a method for descriptor-based synthesis and show that we can control the descriptors of an instrument while keeping its timbre structure.
Sound Audio and Speech Processing
