Semantic Audio Erlangen , Germany 21 – 24

770 J. Audio Eng. Soc., Vol. 64, No. 4, 2016 April Semantic audio is the relatively young field concerned with content-based management of digital audio recordings. The rapid evolution of digital audio technologies—see the ubiquity of data compression and streaming, the emergence of large audio libraries both online and offline, and recent developments in content-based audio retrieval—have significantly changed the way digital audio is created, manipulated, and consumed. The number of available recordings grows greater each day, which is why content-based management of audio data is essential for producers and consumers alike. In addition to audio retrieval and recommendation techniques, the semantics of audio signals are also becoming more important in object-oriented and intelligent production, including recording, editing, and processing. Finally, with an increasing number of devices listening to their environment, “making sense” of audio is more important than ever. Recent product releases demonstrate this, and many more innovations are being unveiled in this area at a very high pace. The third AES International Conference on the topic of semantic audio took place 22–24 June at Fraunhofer IIS in Erlangen, Germany. Previous editions were the 53rd International Conference in London, UK, January 2014, and the 42nd in Ilmenau, Germany, July 2011, hosted by Fraunhofer IDMT, another institute of the same German research organization. This edition was jointly organized by the hosting institution Fraunhofer IIS, Friedrich-Alexander Universität (FAU) Erlangen-Nürnberg, and their shared Audio Labs, and further supported by gold sponsors Native Instruments and Dolby. The conference was chaired by Christian Uhle (Fraunhofer IIS) and Meinard Müller (FAU, AudioLabs). The scientific program was coordinated by the paper chairs Christian Dittmar (FAU, AudioLabs) and Jakob Abeßer (Fraunhofer IDMT). Between the 76 delegates, 15 different countries from Europe, Australia, Asia, and the Americas were represented, with a 30%–70% split between industry professionals and academics. The program committee received 38 paper submissions, of which 27 were accepted and presented as lectures (13) or posters (14). Five delegates also responded to the call for LateBreaking Demos, showcasing recent work alongside the poster presentations. Because of the very nature of semantic audio, the range of topics covered was relatively wide, including work on music, speech, and sound effects. International Conference