AES 42nd Conference: Main page

The 42nd International AES Conference on Semantic Audio

Ilmenau, Germany

The evolution of digital audio technologies, audio compression and streaming has significantly changed the way digital audio is consumed, managed and edited. Personal music collections nowadays comprise up to ten-thousands of music titles. Even mobile devices are able to store some thousands of songs. But these magnitudes are nothing compared to the vast amount of music data digitally available on the Internet. New audio content can be produced at a very low cost, thus user-generated content grows more and more each day.

A multitude of algorithms has been developed in order to tackle the problems that occur when handling these amounts of data. Finding an automatic mapping between audio features and contextual interpretations is the key to solve these. This mapping enables a user to formulate a query for audio content using natural language or at least combinations of semantically meaningful terms. For this task, models describing how music is perceived are needed, as well as methods for the extraction, analysis and representation of linguistic descriptions of music. On the other hand, more sophisticated audio features and analysis of the music structure can narrow the semantic gap. First applications have made their way from ongoing research into consumer applications but these show, that proposed mappings cannot be considered as universally valid. Possibilities for personalization to the users’ preferences as well as context dependency must be investigated as well.
Aside from audio retrieval and recommendation scenarios, understanding the semantics of music has also great potential in object oriented audio coding, audio processing, such as automated or assisted upmixing to multichannel. Furthermore, in audio editing and music games, attempts to interpret the audio material in a task-oriented way are being made. First products prove that development, but a lot more innovative functionalities are at hand.
The conference will give an overview of the present state-of-the-art in a broader perspective, and address many of the new scientific disciplines involved in this still-emerging field. Our purpose is to continue fostering this line of interdisciplinary research in a rapidly expanding and promising field.

Targeted audience
Multidisciplinary researchers, active in signal-processing, social, musicological and usability aspects of semantic audio analysis and processing.

Format and date
A 3-day residential conference held at the campus of Ilmenau University of Technology. The date will be 22nd to 24th of July 2011.

AES - Audio Engineering Society