Output details
11 - Computer Science and Informatics
The University of West London
Recommending Audio Mixing Workflows
<22> This paper describes our work on Audio Advisor, a workflow recommender for audio mixing. We examine the process of eliciting, formalising and modeling the domain knowledge and expert's experience. We describe the effects and problems associated with the knowledge formalisation processes. We employ structured case-based reasoning to capture the vagueness encountered in the audio domain. We used extensive similarity measure modeling to counter the vagueness associated with formalising knowledge about and descriptors of emotions. We employed GATE to process natural language queries within Audio Advisor. We demonstrate the use of the Audio Advisor software prototype and provide a first evaluation.