activity
20242026
collaborators
Showing cs.SDShow all

8 papers · 1 filter

cs.SD2025

Assessing the Alignment of Audio Representations with Timbre Similarity Ratings

Haokun Tian, Stefan Lattner, Charalampos Saitis

Psychoacoustical so-called "timbre spaces" map perceptual similarity ratings of instrument sounds onto low-dimensional embeddings via multidimensional scaling, but suffer from scal…

cs.SD2025

Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching

Ben Hayes, Charalampos Saitis, György Fazekas

Many audio synthesizers can produce the same signal given different parameter configurations, meaning the inversion from sound to parameters is an inherently ill-posed problem. We…

cs.SD2025

Mamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music Generation

Jincheng Zhang, György Fazekas, Charalampos Saitis

The recent surge in the popularity of diffusion models for image synthesis has attracted new attention to their potential for generation tasks in other domains. However, their appl…

cs.SD2025

Designing Neural Synthesizers for Low-Latency Interaction

Franco Caspe, Jordie Shier, Mark Sandler +2

Neural Audio Synthesis (NAS) models offer interactive musical control over high-quality, expressive audio generators. While these models can operate in real-time, they often suffer…

cs.SD2025

Hybrid Losses for Hierarchical Embedding Learning

Haokun Tian, Stefan Lattner, Brian McFee +1

In traditional supervised learning, the cross-entropy loss treats all incorrect predictions equally, ignoring the relevance or proximity of wrong labels to the correct answer. By l…

cs.SD2024

Foundation Models for Music: A Survey

Yinghao Ma, Anders Øland, Anton Ragni +39

In recent years, foundation models (FMs) such as large language models (LLMs) and latent diffusion models (LDMs) have profoundly impacted diverse sectors, including music. This com…