Support vector machine active learning for image retrieval
MULTIMEDIA '01 Proceedings of the ninth ACM international conference on Multimedia
Support vector machine active learning with applications to text classification
The Journal of Machine Learning Research
MARSYAS: a framework for audio analysis
Organised Sound
MARSYAS: a framework for audio analysis
Organised Sound
Music emotion classification: a fuzzy approach
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Music emotion recognition: the role of individuality
Proceedings of the international workshop on Human-centered multimedia
Personalized music emotion recognition
Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
Inter-labeler Agreement for Anger Detection in Interactive Voice Response Systems
IE '10 Proceedings of the 2010 Sixth International Conference on Intelligent Environments
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
Prediction of the Distribution of Perceived Music Emotions Using Discrete Samples
IEEE Transactions on Audio, Speech, and Language Processing
Proceedings of the 20th ACM international conference on Multimedia
| Hi-index | 0.00 |
We propose using active learning in a personalized music emotion classification framework to solve subjectivity, one of the most challenging issues in music emotion recognition (MER). Personalization is the most direct method to tackle subjectivity in MER. However, almost all of the state-of-the-art personalized MER systems require a huge amount user participation, which is a non-neglegible problem in real systems. Active learning seeks to reduce human annotation efforts, by automatically selecting the most informative instances for human relabeling to train the classifier. Experimental results on a Chinese music dataset demonstrate that our method can effectively reduce as much as 80% of the requirement of human annotation without decreasing F-measure. Different query selection criteria of active learning were also investigated, and we found that informativeness criterion which selects the most uncertain instances performed best in general. We finally show the condition of successful active learning in personalized MER is that label consistency from the same user.