Content-Based Indexing of Symbolic Music Documents - Intelligent Music Information Systems: Tools and Methodologies - page 2

Chapter I
Content-Based Indexing of
Symbolic Music Documents

Nicola Orio
University of Padova, Italy

aBstract

Indexing is the core component of most information retrieval systems, because it allows for a compact
representation of the content of a collection of documents, aimed at efficient and scalable access and
retrieval. Indexing techniques can be extended also to music, providing that significant descriptors
are computed from music documents. These descriptors can be defined as the “lexical units” of music,
depend on the dimensions that are taken into account - melody, harmony, rhythm, timbre - and are
related to the way listeners perceive music. This chapter describes some relevant aspects of indexing of
symbolic music documents, giving a review of its basic concepts and going in more detail about some
key aspects, such as the consistency at which candidate index terms are perceived by listeners, the ef-
fectiveness of alternative approaches to compute indexes, and how individual indexing schemes can be
combined together by applying data fusion approaches.

IntoductIon

based multimedia access, the development of new
techniques for indexing, searching and retrieving
multimedia documents have been the focus of
many researchers in IR. The research projects in
digital libraries, and specifically those carried out
in cultural heritage domain, have shown that the
integrated management of diverse media—text,
audio, image, video—is a necessary step (Moen,
1998). As stressed in Sparck Jones and Willett
(1997), the problem with content-based access
to multimedia data is twofold. On the one hand,
each media requires specific techniques that can-

The core problem of Information Retrieval (IR)
is to effectively retrieve documents which convey
content being relevant to the user's information
needs. Effective and efficient techniques have been
developed to index, search and retrieve documents
from collections of hundreds of thousands, or
millions of textual items. The most consolidated
results have been obtained for collections of docu-
ments and user's queries in textual form and in
English language. In order to provide a content-