Small data ai captures unique sounds of persian calligraphy
Small Data Generative AI for Culturally Specific Artistic Creation: A Case Study on the Sonic Space of sarir
SoundComputers and Society
Summary
Large AI models often miss or misrepresent cultural art forms outside the Western world. The authors show that using a small, carefully selected dataset about sarir — a special sound in Persian calligraphy — can help AI learn its unique sound details. They created this dataset and trained AI models that can generate and interact with these sounds in real time. Their approach works better than large generic audio models at capturing this cultural art. This study shows that using small, focused data can help AI engage better with specific cultural artistic traditions.
What this means in practice
- •For digital artists: Create culturally authentic audio effects by training AI on small, focused sound datasets representing unique cultural art forms.
- •For audio software developers: Develop interactive audio tools that generate real-time culturally specific sounds by adapting model training to limited curated datasets.
Authors
Arshia Sobhan, Paul Triana, Philippe Pasquier
Abstract
Large-scale generative AI (GenAI) models have become increasingly integrated into contemporary creative practice, yet they often reproduce cultural biases and fail to meaningfully engage with non-Western artistic traditions. In response, this paper explores a small-data approach that foregrounds artist-curated and culturally informed dataset creation and model training. Through a case study on sarir (the distinctive sound produced by the reed pen in Persian calligraphy), we demonstrate how small-data GenAI can operate within a highly situated cultural context that lies beyond the representational reach of large-scale GenAI models. We construct a bespoke sarir audio dataset and train two models, RAVE and StyleGAN2, adapting each to the sonic domain through audio synthesis and spectrogram generation. The resulting models learn the fine-grained timbral and gestural nuances of sarir, enabling both real-time interaction and extended generative output. By comparing these results with state-of-the-art text-to-audio models, we clearly demonstrate the disparity in their performance and highlight the expressive possibilities unlocked through the small data approach. This focused case study demonstrates the feasibility of small-data GenAI for culturally specific artistic creation and underscores the value of further investigations that extend this approach to other cultural materials and artistic domains.