Interactive design of interpretable features for marine soundscape data annotationThiago S. Gouvêa; Ilira Troshani; Marc Herrlich; Daniel Sonntag
In: Workshop on Human-centered Design of Symbiotic Hybrid Intelligence. Workshop on Human-centered Design of Symbiotic Hybrid Intelligence (HCSHI-2022), located at HHAI, June 14, Amsterdam, Netherlands, HHAI, 2022.
Machine learning (ML) is increasingly used in different application domains. However, to reach its full potential it is important that experts without extensive ML training be able to create and effectively apply models in their domain. This requires forms of co-learning that need to be facilitated by effective interfaces and interaction paradigms. Inspired by the problem of detecting and classifying sound events in marine soundscapes, we are developing Seadash. Through a rapid, iterative data exploration workflow, the user designs and curates features that capture meaningful structure in the data, and uses these to efficiently annotate the dataset. While the tool is still in early stages, we present the concept and discuss future directions.