Research Article
GrainSynth: A Generative Synthesis Tool Based on Spatial Interpretations of Sound Samples
@INPROCEEDINGS{10.1007/978-3-030-76426-5_8, author={Archelaos Vasileiou and Jo\"{a}o Andr\^{e} Mafra Tenera and Emmanouil Papageorgiou and George Palamas}, title={GrainSynth: A Generative Synthesis Tool Based on Spatial Interpretations of Sound Samples}, proceedings={Intelligent Technologies for Interactive Entertainment. 12th EAI International Conference, INTETAIN 2020, Virtual Event, December 12-14, 2020, Proceedings}, proceedings_a={INTETAIN}, year={2021}, month={5}, keywords={Granular synthesis Gestalt principles Data visualization Generative sound Perlin force field Machine learning for audio}, doi={10.1007/978-3-030-76426-5_8} }- Archelaos Vasileiou
João André Mafra Tenera
Emmanouil Papageorgiou
George Palamas
Year: 2021
GrainSynth: A Generative Synthesis Tool Based on Spatial Interpretations of Sound Samples
INTETAIN
Springer
DOI: 10.1007/978-3-030-76426-5_8
Abstract
This paper proposes a generative design approach for the creative exploration of dynamic soundscapes that can be used to generate compelling and immersive sound environments. A granular synthesis tool is considered based on the perceptual self-organization of sound samples by utilizing the t-Stochastic Neighboring Embedded algorithm (t-SNE) for the spatial mapping of sonic grains into a 2D space. The proposed system was able to relate the visual stimuli with the sonic responses in the context of the generic gestalt principles of visual perception. According to user evaluation, the application operated intuitively and also revealed the potential for creative expressiveness both from the user’s perspective and as a standalone, generative synthesizer.
