Abstract
In recent years, the field of Music Emotion Recognition has become established. Less attention has been directed towards the counterpart domain of Audio Emotion Recognition, which focuses upon detection of emotional stimuli resulting from non-musical sound. By better understanding how sounds provoke emotional responses in an audience it may be possible to enhance the work of sound designers.
The work in this paper uses the International Affective Digital Sounds set. Audio features are extracted and used as the input to two machine-learning approaches: regression modelling and artificial neural networks, in order to predict the emotional dimensions of arousal and valence.
It is found that shallow neural networks perform better than a range of regression models. Consistent with existing research in emotion recognition, prediction of arousal is more reliable than that of valence. Several extensions of this research are discussed, including work related to improving data sets as well as the modelling processes.