DMCA
Modeling Music as a Dynamic Texture
| Venue: | IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING |
| Citations: | 19 - 3 self |
BibTeX
@MISC{Barrington_modelingmusic,
author = {Luke Barrington and Antoni B. Chan and Gert Lanckriet},
title = { Modeling Music as a Dynamic Texture},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We consider representing a short temporal fragment of musical audio as a dynamic texture, a model of both the timbral and rhythmical qualities of sound, two of the important aspects required for automatic music analysis. The dynamic texture model treats a sequence of audio feature vectors as a sample from a linear dynamical system. We apply this new representation to the task of automatic song segmentation. In particular, we cluster audio fragments, extracted from a song, as samples from a dynamic texture mixture (DTM) model. We show that the DTM model can both accurately cluster coherent segments in music and detect transition boundaries. Moreover, the generative character of the proposed model of music makes it amenable for a wide range of applications besides segmentation. As an example, we use DTM models of songs to suggest possible improvements in some other music information retrieval applications such as music annotation and similarity.
Keyphrases
dynamic texture dtm model musical audio generative character audio fragment detect transition boundary automatic song segmentation new representation dynamic texture mixture automatic music analysis rhythmical quality music information retrieval application dynamic texture model linear dynamical system important aspect cluster coherent segment audio feature vector possible improvement short temporal fragment music annotation wide range
