Eavesdropping v2: Interactive Mood Ecology

The second version of Eavesdropping was developed to continue exploring audience inter-awareness while addressing issues of audience agency raised in the first version. This version also extended the artificial intelligence of the system in validating the mood tagging of audio files. This version removes the composition environment and instead requests the participants to enter their own moods. The system then selects audio files which match those moods to perform in the room while finding files that mix well with each other. Users respond whether they feel the music matches their mood. This is recorded by a machine learning system to improve the mapping of music files to moods.

Eavesdropping Version 2 Online

Performances:

• ACM Multimedia Conference Presentation. October 2008. Vancouver, BC.
• Social Behaviors in Music Workshop. IEEE Conference on Computational Science and Engineering. August 2009. Vancouver, BC.

Publications:

• Stockholm, J., Pasquier, P. "Reinforcement Learning of Listener Response for Mood Classification of Audio." Computational Science and Engineering, IEEE International Conference on, vol. 4, pp. 849-853, 2009 International Conference on Computational Science and Engineering, 2009.
• Stockholm, J., Pasquier, P. "Eavesdropping: Audience Interaction in Network Audio Performance." In Proceeding of the 16th ACM international Conference on Multimedia. Vancouver, BC. Oct. 26-31 2008. MM '08. ACM, New York, NY, 559-568.
• Stockholm, Jack. "Eavesdropping: Network Mediated Performance in Social Space." Leonardo Music Journal, 18 (2008): 55-58.