AES New York 2013
Thursday, October 17, 5:00 pm — 6:30 pm (Room 1E14)
W9 - Can We Measure Emotions?Chair:
Judith Liebetrau, Ilmenau University of Technology - Ilmenau, Germany; Fraunhofer Institute for Digital Media Technology IDMT - Ilmenau, Germany
Frederik Nagel, Fraunhofer Institute for Integrated Circuits IIS - Erlangen, Germany; International Audio Laboratories - Erlangen, Germany
Mark B. Sandler, Queen Mary University of London - London, UK
Chia-Jung Tsay, University College London - London, UK
Music evokes and carries emotions. Music emotion recognition (MER), as a part of music information retrieval (MIR), examines the question: Which parts of music evoke what emotions and how can they be automatically classified? Classification systems need to be trained in terms of feature selection and prediction. As training data, musical pieces of which the average emotional impact is known have to be used. Due to the subjectivity of emotions, the generation of such ground truth data poses several challenges. In this workshop obstacles in measuring and automatically predicting emotions evoked by music will be displayed.
Among others, the workshop will address the following topics: What is an emotion and how can it be defined? Is there a difference between felt and perceived emotion? Can the emotional impact of a musical piece be subjectively measured? Can the emotional impact of a musical piece be predicted?
|This session is presented in association with the AES Technical Committee on Perception and Subjective Evaluation of Audio Signals|