Tim Pohle, Elias Pampalk, Gerhard Widmer,
"Evaluation of Frequently Used Audio Features for Classification of Music into Perceptual Categories"
: Proceedings of the Fourth International Workshop on Content-Based Multimedia Indexing (CBMI´05), Riga, Lativa, 2005
Evaluation of Frequently Used Audio Features for Classification of Music into Perceptual Categories
Sprache des Titels:
Proceedings of the Fourth International Workshop on Content-Based Multimedia Indexing (CBMI´05), Riga, Lativa
The ever-growing amount of available music induces an
increasing demand for Music Information Retrieval (MIR)
applications such as music recommendation applications or
automatic classification algorithms.
When audio-based, a crucial part of such systems are the
audio feature extraction routines. In this paper, we evaluate
how well a variety of combinations of feature extraction
andmachine learning algorithms are suited to classifymusic
into perceptual categories. The examined categorizations
are perceived tempo, mood (happy / neutral /sad), emotion
(soft / neutral / aggressive), complexity, and vocal content.
The aim is to contribute to the investigation which aspects
of music are not captured by the common audio descriptors;
from our experiments we can conclude that most
of the examined categorizations are not captured well. This
indicates that more research is needed on alternative (possibly
extra-musical) sources of information for useful music