Thumbnail
Access Restriction
Open

Author Benetos, Emmanouil ♦ Kotropoulos, Constantine
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Gtzan Dataset ♦ Supervised Ntf Classifier ♦ Automatic Music Genre Classification ♦ Feature Vector ♦ Feature Matrix ♦ Standard Deviation ♦ Feature Tensor ♦ Support Vector Machine ♦ N-dimensional Raw Feature Tensor ♦ Frobenius Norm ♦ Pattern Recognition Algorithm ♦ Novel Al-gorithm ♦ Automatic Music Genre Clas-sification System ♦ Non-negative Tensor Factorization ♦ Matrix-based One ♦ Non-negative Matrix Factorization Clas-sifiers ♦ Tensor-based Approach ♦ Sound Description Feature ♦ Genre Classification Accuracy ♦ Tensor Representation ♦ Multilayer Perceptrons ♦ Genre Class ♦ Elemen-tary Rank-1 Tensor ♦ Music Genre Classification Technique ♦ Ntf Classifier
Description in Proc. 16th European Signal Processing Conf
Most music genre classification techniques employ pattern recognition algorithms to classify feature vectors extracted from recordings into genres. An automatic music genre clas-sification system using tensor representations is proposed, where each recording is represented by a feature matrix over time. Thus, a feature tensor is created by concatenating the feature matrices associated to the recordings. A novel al-gorithm for non-negative tensor factorization (NTF), which employs the Frobenius norm between an n-dimensional raw feature tensor and its decomposition into a sum of elemen-tary rank-1 tensors, is developed. Moreover, a supervised NTF classifier is proposed. A variety of sound description features are extracted from recordings from the GTZAN dataset, covering 10 genre classes. NTF classifier perfor-mance is compared against multilayer perceptrons, support vector machines, and non-negative matrix factorization clas-sifiers. On average, genre classification accuracy equal to 75 % with a standard deviation of 1 % is achieved. It is demonstrated that NTF classifiers outperform matrix-based ones. 1.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2008-01-01