High-Level Analysis of Audio Features for Identifying Emotional Valence in Human Singing

Stuart Cunningham, Jonathan Weinel, Richard Picking

Research output: Chapter in Book/Report/Conference proceedingConference proceedingpeer-review

4 Citations (Scopus)


Emotional analysis continues to be a topic that receives much attention in the audio and music community. The potential to link together human affective state and the emotional content or intention of musical audio has a variety of application areas in fields such as improving user experience of digital music libraries and music therapy. Less work has been directed into the emotional analysis of human acapella singing. Recently, the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) was released, which includes emotionally validated human singing samples. In this work, we apply established audio analysis features to determine if these can be used to detect underlying emotional valence in human singing. Results indicate that the short-term audio features of: energy; spectral centroid (mean); spectral centroid (spread); spectral entropy; spectral flux; spectral rolloff; and fundamental frequency can be useful predictors of emotion, although their efficacy is not consistent across positive and negative emotions
Original languageEnglish
Title of host publicationProceedings of the Audio Mostly 2018 on Sound in Immersion and Emotion
PublisherAssociation for Computing Machinery (ACM)
ISBN (Electronic)978-1-4503-6609-0
Publication statusPublished - 2018
EventAudio Mostly 2018: Sound in Immersion and Emotion - Wrexham, United Kingdom
Duration: 12 Sept 201814 Sept 2018


ConferenceAudio Mostly 2018
Country/TerritoryUnited Kingdom
Internet address


Dive into the research topics of 'High-Level Analysis of Audio Features for Identifying Emotional Valence in Human Singing'. Together they form a unique fingerprint.

Cite this