Paper Info
Title
Emotion tracking in music using continuous conditional random fields and relative feature representation.
Abstract
Digitization of how people acquire music calls for better music information retrieval techniques, and dimensional emotion tracking is increasingly seen as an attractive approach. Unfortunately, the majority of models we still use are borrowed from other problems that do not suit emotion prediction well, as most of them tend to ignore the temporal dynamics present in music and/or the continuous nature of Arousal-Valence space. In this paper we propose the use of Continuous Conditional Random Fields for dimensional emotion tracking and a novel feature vector representation technique. Both approaches result in a substantial improvement on both root-mean-squared error and correlation, for both short and long term measurements. In addition, they can both be easily extended to multimodal approaches to music emotion recognition.
Year
DOI
Venue
2013
10.1109/ICMEW.2013.6618357
IEEE International Conference on Multimedia and Expo Workshops
Keywords
Field
DocType
Arousal-Valence space,continuous emotions,machine learning,feature representation,acoustic features
Digitization,Computer science,Emotion recognition,Music emotion recognition,Artificial intelligence,Conditional random field,Computer vision,Music information retrieval,Feature vector,Pattern recognition,Feature extraction,Speech recognition,Correlation,Machine learning
Conference
ISSN
Citations 
PageRank 
2330-7927
7
0.56
References 
Authors
12
3
Name
Order
Citations
PageRank
Vaiva Imbrasaite180.91
Tadas Baltrusaitis268330.42
Peter Robinson31438129.42