Music expression understanding based on a joint semantic space
Luca Mion and Giovanni De Poli
The 10th Congress of the Italian Association for Artificial Intelligence - AI for Expressive Media (AIIA-EM 2007)
Roma, Italy, September 10-13, 2007
Abstract
A paradigm for music expression understanding based on a joint semantic space, described by both affective and sensorial adjectives, is presented. Machine learning techniques were employed to select and validate relevant low level features, and an interpretation of the clustered organization based on action and physical analogy is proposed.