Improving Audio Retrieval through Loudness Profile Categorization

The increasing popularity of audio content sharing in online platforms requires the development of techniques to better organize and retrieve this data. In this paper we look at how to improve similarity search through content categorization in the context of Freesound, a popular online sound sharing site. We focus on organization based on morphological description. In particular, we propose to improve search results by incorporating information about query sound's loudness profile. This is performed within a thresholding based framework and can be generalized to structure information about the temporal evolution of other sound attributes. We perform a subjective evaluation to demonstrate the practical relevance of our method.