Amatriain, XavierBonada, Jordi, 1973-Loscos, ÀlexArcos, Josep LluísVerfaille, Vincent2019-06-282019-06-282003Amatriain X, Bonada J, Loscos À, Arcos JL, Verfaille V. Content-based transformations. J New Music Res. 2003;32(1):95-114. DOI: 10.1076/jnmr.30.1.39.71190929-8215http://hdl.handle.net/10230/41895Content processing is a vast and growing field that integratesdifferent approaches borrowed from the signal processing,information retrieval and machine learning disciplines. Inthis article we deal with a particular type of content pro-cessing: the so-called content-based transformations. We willnot focus on any particular application but rather try to givean overview of different techniques and conceptual implica-tions. We first describe the transformation process itself,including the main model schemes that are commonly used,which lead to the establishment of the formal basis for a definition of content-based transformations. Then we take aquick look at a general spectral based analysis/synthesisapproach to process audio signals and how to extract featuresthat can be used in the content-based transformation context.Using this analysis/synthesis approach we give some exam-ples on how content-based transformations can be applied tomodify the basic perceptual axis of a sound and how we caneven combine different basic effects in order to perform moremeaningful transformations. We finish by going a step furtherin the abstraction ladder and present transformations that arerelated to musical (and thus symbolic) properties rather thanto those of the sound or the signal itself.application/pdfeng© This is an Accepted Manuscript of an article published by Taylor & Francis in Journal of new music research on 2003, available online: http://www.tandfonline.com/10.1076/jnmr.30.1.39.7119info:eu-repo/semantics/articlehttp://dx.doi.org/10.1076/jnmr.30.1.39.7119info:eu-repo/semantics/openAccess