Descriptor sub-representations in semantic equalisation
暂无分享,去创建一个
In semantic equalisation, descriptions of audio transformations can be used to control low-level audio effect parameters. In this paper, we explore sub-representations of these descriptions in order to suggest more contextually relevant processing parameters to users, based on external influence. We propose a methodology for finding sub-representations, and an intuitive low-dimensional interface, which can be used to recommend equalisation curves based on proximity to cluster centroids.
[1] György Fazekas,et al. SAFE: A System for the Extraction and Retrieval of Semantic Audio Descriptors , 2014 .
[2] Bryan Pardo,et al. Social-EQ: Crowdsourcing an Equalization Descriptor Map , 2013, ISMIR.
[3] Joshua D. Reiss,et al. Semantic Description of Timbral Transformations in Music Production , 2016, ACM Multimedia.
[4] Spyridon Stasis,et al. A model for adaptive reduced-dimensionality equalisation , 2015 .