Information Technology Reference
In-Depth Information
Chapter IX
Music Information Retrieval in
P2P Networks
1
Ioannis Karydis
Aristotle University of Thessaloniki, Greece
Yannis Manolopoulos
Aristotle University of Thessaloniki, Greece
aBstract
In this chapter we present the most significant trends in recent research in the field of content-based
music information retrieval in peer-to-peer networks. Despite the diminished attention the area has
received in general terms, the relatively close area of metadata MIR in P2P is by far new. As metadata
prove to be inefficient for the purposes of MIR as well as the peculiarities of music in comparison to text
and image data, developing dedicated solutions for CBMIR in P2P networks becomes a necessity while
the challenges faced therein, unique. Depending on the type of P2P network, a number of prominent
research works are presented and compared in this chapter.
IntroductIon
abundantly used, even nowadays, traditional meta-
data (title, composer, performer, genre, date, etc.)
of a music object give rather minimal information
regarding the actual content of the music object
itself. On the other hand, research efforts in the
field of music information retrieval (MIR) have
developed efficient methods for searching music
data collections by
content
. For instance, queries
based on humming (using a microphone) or on a
small piece of musical file, are far more natural an
approach to MIR. This type of queries lies within
the content-based MIR (CBMIR). In CBMIR, an
The World Wide Web (WWW) is being used
for commercial, entertainment, and educational
purposes and has become the primary means for
information dissemination. One popular type of
data that is being disseminated over WWW is digi-
tised music. Recently, the new opportunities that
emerge from this activity have been recognized
and led to the development of systems like iTune
(www.apple.com/itunes), iMusic (www.imusic.
com), and Napster (www.napster.com). Although
Search WWH ::
Custom Search