Reinforcement Learning of Listener Response for Mood Classification of Audio

This paper describes a method of applying a reinforcement learning artificial intelligence to categorize audio files by mood based on listener response during a performance. The system discussed is implemented in a performance art environment designed to present the moods of multiple participants simultaneously in a room via a diffusion of representative audio samples.

• Type: Conference
• Year: 2009
• Where: CSE
• Authors: Jack Stockholm, Philippe Pasquier
• Keywords: Computer Science And Engineering, CSE 2009, Listener Response, Performance Art Environment, Representative Audio Samples