A Supra-Classifier Architecture for Scalable Knowledge Reuse
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
A Large-Scale Evaluation of Acoustic and Subjective Music-Similarity Measures
Computer Music Journal
Extracting information from music audio
Communications of the ACM - Music information retrieval
Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
Incorporating machine-learning into music similarity estimation
Proceedings of the 1st ACM workshop on Audio and music computing multimedia
Virtual microphones for multichannel audio resynthesis
EURASIP Journal on Applied Signal Processing
Improving automatic music tag annotation using stacked generalization of probabilistic SVM outputs
MM '09 Proceedings of the 17th ACM international conference on Multimedia
FMF: Query adaptive melody retrieval system
Journal of Systems and Software
Audio feature engineering for automatic music genre classification
Large Scale Semantic Access to Content (Text, Image, Video, and Sound)
Genre classification of symbolic music with SMBGT
Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments
Hi-index | 0.00 |
This paper describes a method of mapping music into a semantic space that can be used for similarity measurement, classification, and music information retrieval. The value along each dimension of this anchor space is computed as the output from a pattern classifier which is trained to measure a particular semantic feature. In anchor space, distributions that represent objects such as artists or songs are modeled with Gaussian mixture models, and several similarity measures are defined by computing approximations to the Kullback-Leibler divergence between distributions. Similarity measures are evaluated against human similarity judgements. The models are also used for artist classification to achieve 62% accuracy on a 25-artist set, and 38% on a 404-artist set (random guessing achieves 0.25%). Finally, we describe a music similarity browsing application that makes use of the fact that anchor space dimensions are meaningful to users.