PUB - Publikationen an der Universität Bielefeld

This paper introduces the Generative Sample Map (GESAM), a novel two-stage unsupervised learning framework capable of generating high-quality and expressive audio samples for music production. Recent generative approaches based on language models rely on text prompts as conditions. However, fine nuances in musical audio samples can hardly be described in the modality of text. For addressing this shortcoming, we propose to learn a highly descriptive latent 2D audio map by a Variational Autoencoder (VAE) which is then utilized for conditioning a Transformer model. We demonstrate the Transformer model's ability to achieve high generation quality and compare its performance against two baseline models. By selecting points on the map that compresses the manifold of the audio training set into 2D, we enable a more natural interaction with the model. We showcase this capability through an interactive demo interface, which is accessible on our website https://limchr.github.io/gesam/