Dr. Hendrik Purwins is a Juan de la Cierva research fellow at Music Technology Group, Universitat Pompeu Fabra, Barcelona.
His current research interests include unsupervised learning for generative models of music and environmental sounds, musical
surprise and expectation, voice driven music-computer interaction, models of tonality, automatic analysis of melodic ornamentation, and failure prediction in semi conductor production lines. He has been visting researcher at IRCAM, Paris, CCRMA, Stanford, McGill University, Montreal, visiting professor at UPF, Barcelona, and research fellow at TU Berlin. He has co-coordinated work packages in two large European projects on music cognition and sound design (http://emcap.iua.upf.es/, http://closed.ircam.fr/). In the European IMPROVE project he applied statistical methods for automatic fault detection and
prediction in manufacturing for the semi-conductor industry (Infineon, AMS). He has obtained a PhD "Profiles of Pitch Classes" at the Neural Information Processing Group at Technische Universität Berlin, receiving a scholarship from the Studienstiftung des deutschen Volkes. Before that he had studied mathematics at Bonn and Münster University, completing a diploma in pure mathematics (all grades 'A'). He also completed course work in musicology, electroacoustic composition, music theory, and acting at the Musikhochschule Köln and Universität der Künste, Berlin. Starting with playing the violin at age of 7, he has played several string quartet and orchestra concerts during his mandatory military service with the professional German head quarters chamber orchestra. He (co-)authored almost 50 scientific papers mostly on machine listening, statistical music analysis, music generation, and sound and music perception. For more information, click here