(Georgia Institute of Technology, 2016-04)
Perez-Carrillo, Alfonso; Thalmann, Florian; Fazekas, György; Sandler, Mark
We present a web-based cross-platform adaptive music player that combines music information retrieval (MIR) and audio
processing technologies with the interaction capabilities
offered by GPS-equipped mobile devices. The application
plays back a list of music tracks, which are linked
to geographic paths in a map. The music player has two main enhanced features that adjust to the location of the
user, namely, adaptable length of the songs and automatic
transitions between tracks. Music tracks are represented as
data packages containing audio and metadata (descriptive
and behavioral) that builds on the concept of Digital Music
Object (DMO). This representation, in line with nextgeneration
web technologies, allows for
exible production
and consumption of novel musical experiences. A content
provider assembles a data pack with music, descriptive analysis
and action parameters that users can experience and
control within the restrictions and templates defined by the
provider.
(Georgia Institute of Technology, 2016-04)
Allik, Alo; Fazekas, György; Barthet, Mathieu; Swire, Mark
myMoodplay is a web app that allows users to interactively
discover music by selecting desired emotions. The application uses the Web Audio API, JavaScript animation for
visualisation, linked data formats and affective computing
technologies. We explore how artificial intelligence, the Semantic Web and audio synthesis can be combined to provide new personalised online musical experiences. Users can
choose degrees of energy and pleasantness to shape the desired musical mood trajectory. Semantic Web technologies
have been embedded in the system to query mood coordinates from a triple store using a SPARQL endpoint and to
connect to external linked data sources for metadata.