Sound Trace Flow Composition: A Method for Generating Abstract Visual Forms from Acoustic Features
DOI:
https://doi.org/10.54097/qkc6qf33Keywords:
Sound-to-Visual Mapping, Visual Abstraction, Generative ArtAbstract
This paper introduces Sound Trace Flow Composition, a rule-based method for converting birdsong features into abstract visual structures. We extract and normalise four features: RMS energy, spectral centroid, frequency-band energy ratios, and zero-crossing rate, to influence flow lines, density, geometric fragmentation, continuity, and negative space. The composition is organised using a Bézier-based framework, and controlled randomness is incorporated to vary the composition within constraints derived from the source. The method preserves the temporal and spectral differences of different birdsong samples in a non-conventional manner by applying a shared visual grammar to them, avoiding reduction to conventional data plots. It bridges explicit sound-to-visual mappings and generative art by providing traceable relationships, constrained variation, and reproducible visual construction.
Downloads
References
[1] Lima, H. B., dos Santos, C. G. R., & Meiguins, B. S. (2021). A survey of music visualization techniques. ACM Computing Surveys, 54(7), 1 29. https://doi.org/10.1145/3461835.
[2] Foote, J. (1999). Visualizing music and audio using self similarity. Proceedings of the Seventh ACM International Conference on Multimedia, 77 80. https://doi.org/ 10.1145/ 319463. 319472.
[3] Dzwonczyk, L., Cella, C. E., & Ban, D. (2024). Network bending of diffusion models for audio visual generation. Proceedings of the 27th International Conference on Digital Audio Effects (DAFx24).
[4] Tzanetakis, G., & Cook, P. (2002). Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing, 10(5), 293 302. https://doi.org/10.1109/ TSA. 2002. 800560.
[5] Grill, T., & Flexer, A. (2012). Visualization of perceptual qualities in textural sounds. Proceedings of the International Computer Music Conference (ICMC 2012).
[6] Spence, C. (2011). Crossmodal correspondences: A tutorial review. Attention, Perception, & Psychophysics, 73(4), 971 995. https://doi.org/10.3758/s13414 010 0073 7.
[7] Rodrigues, A., Sousa, B., & Cardoso, A. (2022). “Found in translation”: An evolutionary framework for auditory visual relationships. Entropy, 24(12), 1706. https://doi.org/10. 3390/ e24121706.
[8] Shim, J. Y., Kim, J., & Kim, J. K. (2023). Audio to visual cross modal generation of birds. IEEE Access, 11, 27719 27729. https://doi.org/10.1109/ACCESS.2023.3257565.
[9] Kim, S. B., Senocak, A., & Ha, H. (2023). Sound to visual scene generation by audio to visual latent alignment. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6430 6440.
[10] Lee, C. C., Lin, W. Y., & Shih, Y. T. (2020). Crossing you in style: Cross modal style transfer from music to visual arts. Proceedings of the 28th ACM International Conference on Multimedia. https://doi.org/10.1145/3394171.3413624.
[11] Chen, Z., Geng, D., & Owens, A. (2024). Images that sound: Composing images and sounds on a single canvas. Advances in Neural Information Processing Systems 37. https://doi.org/ 10. 52202/079017 2700.
[12] Routray, P. K., Nagpal, M., & Gupta, M. (2025). AI generated visualizations of musical patterns. ShodhKosh: Journal of Visual and Performing Arts, 6(2s), 168 178. https://doi.org/10. 29121/shodhkosh.v6.i2s.2025.6697.
[13] Patra, B., Jeyanthi, P., & Bhardwaj, R. (2025). Cross disciplinary art through AI generated music and visuals. ShodhKosh: Journal of Visual and Performing Arts, 6(4s), 245 254. https://doi.org/10.29121/ shodhkosh. v6.i4s. 2025. 6832.
[14] Liu, Y., Luan, H., & Liu, D. (2026). ChladniSonify: A visual acoustic mapping method for Chladni patterns in new media art creation [Preprint]. arXiv. https://arxiv.org/ abs/ 2605. 09846.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Highlights in Art and Design
This work is licensed under a Creative Commons Attribution 4.0 International License.
