Project “Spoken Songs” researchers participate in workshop in Tartu

Last week, colleagues Linda Luīze Barbare and Kārlis Freivalds participated in the international Workshop on Uncertainty in Machine Learning (WUML 2026), held at the University of Tartu from February 2 to 4.

The poster "Analysis of Latvian Spoken Songs Using Artificial Intelligence" was presented at the workshop, introducing the international research community to studies conducted at the Institute of Literature, Folklore and Art of the University of Latvia regarding spoken songs and their digital analysis. The poster outlines experiments with Optical Music Recognition (OMR) and artificial intelligence methods that assist in analyzing the melodic and textual variations of spoken songs.

The research is conducted within the framework of the FLPP project "Spoken Songs: Algorithms of Composition and Improvisation" (No. lzp-2025/1-0252).