@ARTICLE\{IMM2007-04023,
    author       = "A. Meng and P. Ahrendt and J. Larsen and L. K. Hansen",
    title        = "Temporal Feature Integration for Music Genre Classification",
    year         = "2007",
    month        = "jul",
    keywords     = "Temporal Feature integration, autoregressive model, music genre classification",
    pages        = "1654-1664",
    journal      = "",
    volume       = "15",
    editor       = "",
    number       = "5",
    publisher    = "{IEEE} Transactions on Audio and Speech and Language Processing",
    url          = "http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4244528",
    abstract     = "Temporal feature integration is  the process of combining all the feature
vectors in a time frame into a single feature vector in order to
capture the relevant temporal information in the frame. The mean and variance
along the temporal dimension are often used for temporal feature
integration, but they capture neither the temporal dynamics nor
dependencies among the individual feature dimensions. Here, a
multivariate autoregressive feature model is proposed to solve
this problem for music genre classification. This model gives two
different feature sets, the {DAR} and {MAR} features, which are
compared against the baseline mean-variance as well as two other
temporal feature integration techniques. Reproducibility in
performance ranking of temporal feature integration methods
were demonstrated using two data sets with five and eleven music genres, and by using four
different classification schemes. The methods were further compared to
human performance. The proposed {MAR} features perform significantly
better than the other features without much increase in
computational complexity.",
    isbn_issn    = "ISSN: 1558-7916"
}