Cunningham, Stuart, Ridley, Harrison, Weinel, Jonathan ORCID: https://orcid.org/0000-0001-5347-3897 and Picking, Richard (2019) Audio emotion recognition using machine learning to support sound design. In: AM'19: Proceedings of the 14th International Audio Mostly Conference: A Journey in Sound. September 18 - 20, 2019. Association for Computing Machinery (ACM), New York, pp. 116-123. ISBN 9781450372978 (doi:10.1145/3356590.3356609)

PDF (Table of Contents) 34062_WEINEL_Audio_emotion_recognition.pdf - Published Version Restricted to Repository staff only Download (2MB) | Request a copy

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.

Item Type:	Conference Proceedings
Title of Proceedings:	AM'19: Proceedings of the 14th International Audio Mostly Conference: A Journey in Sound. September 18 - 20, 2019
Uncontrolled Keywords:	machine learning, affective computing, audio, emotion, sound design
Subjects:	M Music and Books on Music > M Music Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS) Faculty of Liberal Arts & Sciences > Sound-Image Research Group Faculty of Engineering & Science
Related URLs:	Publisher
Last Modified:	04 Mar 2022 13:06
URI:	http://gala.gre.ac.uk/id/eprint/34062

Actions (login required)

View Item

Downloads