Mercurial > hg > musicweb-iswc2016
changeset 8:d4d732b8b9cb
intro
| author | mariano |
|---|---|
| date | Fri, 29 Apr 2016 09:37:29 +0100 |
| parents | 7a4eb30ea325 |
| children | 9866ea2d3b9a |
| files | musicweb.tex |
| diffstat | 1 files changed, 29 insertions(+), 13 deletions(-) [+] |
line wrap: on
line diff
--- a/musicweb.tex Thu Apr 28 17:44:18 2016 +0100 +++ b/musicweb.tex Fri Apr 29 09:37:29 2016 +0100 @@ -161,23 +161,24 @@ \end{abstract} \section{Introduction}\label{sec:introduction} -In recent years we have witnessed an explosion of information, a consequence of millions of users producing and consuming web resources. Researchers and industry have recognised the potential of this data, and have endeavoured to develop methods to handle such a vast amount of information: to understand and manage it, to transform into knowledge. Multimedia content providers have devoted a lot of energy to analysing consumer preference, in an effort to offer customised user experiences. Music stream services, for instance, carry out extensive analysis trying to identify patterns in user's listening habits, and researchers are striving to refine multimedia recommendation algorithms\cite{Song2012}. There are, however, limitations in user-preference based approaches: recommendations based solely on user preference can very easily lead to a ''rich-club phenomenon''\cite{Zhou2004}, in which the short-tail popular music is heavily reinforced whereas most of the music available online is ignored and remains unknown\cite{Celma2010}. Music recommendation systems such as +In recent years we have witnessed an explosion of information, a consequence of millions of users producing and consuming web resources. Researchers and industry have recognised the potential of this data, and have endeavoured to develop methods to handle such a vast amount of information: to understand and manage it, to transform into knowledge. Multimedia content providers have devoted a lot of energy to analysing consumer preference, in an effort to offer customised user experiences. Music stream services, for instance, carry out extensive analysis trying to identify patterns in user's listening habits, and researchers are striving to refine multimedia recommendation algorithms. There are two main approaches to music recommendation\cite{Song2012}: the first is known as \emph{collaborative filtering}\cite{Su2009}, which recommends music items based on the choices of similar users. There are, however, limitations in user-preference based systems: recommendations based solely on user preference can easily lead to a ''rich-club phenomenon''\cite{Zhou2004}, in which short-tail popular music is heavily reinforced whereas most of the music available online is ignored and remains unknown\cite{Celma2010}. The second most significant model of music recommendation is based on audio content analysis, or \emph{music information retrieval}. This analysis extracts low to high-level audio features such as tempo, key, metric structure, melodic and harmonic sequences, instrument recognition and song segmentation, which are then used to measure music similarity\cite{Aucoutourier2002}, to carry out genre classification or to identify the mood of the song\cite{Kim2010}. Music discovery websites such as Last.fm\footnote{http://www.last.fm}, Allmusic\footnote{http://www.allmusic.com} or Pandora\footnote{http://www.pandora.com} have successfully developed hybrid systems which combine both approaches. + \begin{itemize} -\item Why are we doing this? +\item NOTE: The problem with this is that it does not offer music \emph{discovery}! +\item Music metadata can improve this +\item Pachet's patper on metadata identifies three different kinds of music metadata \begin{itemize} - \item What does the application do? - \item Why is this a good thing? - \item Who is it good for?: User experience. - \item Who is it potentially good for? - + \item Editorial metadata + \item Cultural metadata + \item Acoustic metadata \end{itemize} \end{itemize} + + \section{Background}\label{sec:background} \begin{itemize} \item Information management -\item Music data collection: Spotify has acquired Echonest for \$100 million. -\item Music recommendation systems: many recommendation systems are based on identifying trends in user listening patterns: it likely that a user who likes a particular artist will also like another artist because other users have shown this tendency. \item Some references to semantic web audio \item Linked musicians: echonest, musicbrainz \item Smart music @@ -207,11 +208,16 @@ \vspace{-1em}\begin{thebibliography}{5} % - \bibitem{Song2012} + \bibitem{Song2012} Y.~Song, S.~Dixon and M.~Pearce. \newblock A survey of music recommendation systems and future perspectives \newblock In {\em Proceedings of the 9th International Symposium on Computer Music Modelling and Retrieval}, 2012. - + + \bibitem{Su2009} + X.~Su and T. M. ~Khoshgoftaar. + \newblock A Survey of Collaborative Filtering Techniques. + \newblock In {\em Advances in Artificial Intelligence,(Section 3):1–19}, 2009. + \bibitem{Zhou2004} S.~Zhou and R. J.~Mondrag\'on \newblock The rich-club phenomenon in the Internet topology @@ -221,8 +227,18 @@ O.~Celma \newblock Music Recommendation and Discovery:The Long Tail, Long Fail, and Long Play in the Digital Music Space. \newblock Springer Verlag, Heidelberg, 2010. - - \bibitem{FazekasRJS10_OMRAS2} + + \bibitem{Aucoutourier2002} + J. J.~Aucouturier and F~Pachet. + \newblock Music Similarity Measures: What is the Use. + \newblock In {emProceedings of the ISMIR, pages 157–163}, 2002. + + \bibitem{Kim2010} + Y.E.~Kim, E.M.~Schmidt, R.~Migneco, B.G.~Morton, P.~Richardson, J.~Scott, J.A.~Speck and D.~Turnbull. + \newblock Music Emotion Recognition: A State of the Art Review. + \newblock In {\em Proc. of the 11th Intl. Society for Music Information Retrieval (ISMIR) Conf}, 2010. + + \bibitem{FazekasRJS10_OMRAS2} G.~Fazekas, Y.~Raimond, K.~Jakobson, and M.~Sandler. \newblock An overview of semantic web activities in the {OMRAS2} project. \newblock {\em Journal of New Music Research (JNMR)}, 39(4), 2010.