Mercurial > hg > musicweb-iswc2016
changeset 50:b573e6a3f08c
typos
| author | mariano |
|---|---|
| date | Sun, 01 May 2016 05:48:08 +0100 |
| parents | 388a1d46f00f |
| children | 23b8bfe481b1 |
| files | musicweb.tex |
| diffstat | 1 files changed, 7 insertions(+), 149 deletions(-) [+] |
line wrap: on
line diff
--- a/musicweb.tex Sun May 01 05:43:48 2016 +0100 +++ b/musicweb.tex Sun May 01 05:48:08 2016 +0100 @@ -161,18 +161,6 @@ \keywords{Semantic Web, Linked Open Data, music metadata, semantic audio analysis, music information retrieval } \end{abstract} -% GUIDELINES -% We strongly encourage authors to clearly expose (1) limitations of existing (if any) “non-semantics” approaches that address similar challenges, (2) benefits of semantic technologies (e.g., measurable impacts such as accuracy, scalability, usability or functionality) in real-world settings, and (3) lessons learned from experimentation and / or large scale deployment. - -% We therefore expect submissions to the Applications (Emerging, In-Use, Industry) Track to contain at least the following elements: - -% A clear description and motivation of the problem being addressed, and of its importance in the corresponding domain -% A description of the system, application or tool developed that clearly shows the role that semantic technologies and principles are playing in its architecture, or the contribution helping the adoption of semantic technologies and principles -% A clear statement about the current user / client base of the system, application or tool (including size and composition, e.g. domain experts, developers, etc.), as well as plans for deployment/adoption -% For In-Use papers: A discussion on the benefits and challenges associated with the use of semantic technologies and principles in the considered scenarios, both from a technical (what the technology enables) and a non-technical (e.g. development effort required, effect on user interaction/satisfaction, policy-related issues) point of view -% For Industry papers: A clear description of the impact in the respective industry and motivation for the need of semantic web technologies. -% For Emerging applications: A clear description on requirements or next steps for large scale deployment in real world settings. The Semantic Web community should benefit from lessons learned / advices for emerging applications to be deployed in large scale environments. - \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. 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. The second model is based on audio content analysis, or \emph{music information retrieval}. The task here is to extract 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. @@ -242,24 +230,16 @@ \end{figure} The global MusicBrainz identifiers enable convenient and concise means to disambiguate between potential duplicates or irregularities in metadata across resources, a problem which is all too common in systems relying on named entities. Besides identifiers, the MusicBrainz infrastructure is also used for the search functionality of MusicWeb. However, in order to query any information in DBpedia, the MusicBrainz identifiers need to be associated with a DBpedia resource, which is a different kind of identifier. This mapping is achieved by querying the Sameas.org co-reference service to retrieve the corresponding DBpedia URIs. The caveat in this process is that Sameas does not actually keep track of MusicBrainz artist URIs, however, by substituting the domain for the same artist's URI in the BBC domain\footnote{\url{http://www.bbc.co.uk/music/artists/}}, the service can get around this obstacle. Once the DBpedia artist identity is determined, the service proceeds to construct the majority of the profile, including the biography and most of the linking categories to other artists. The standard categories available include associated artists and artists from the same hometown, while music group membership and artist collaboration links are queried from MusicBrainz. The core of the Semantic Web linking functionality is provided by categories from YAGO. The Spotify\footnote{historically the Echonest} and Last.fm APIs are used for recommendations that are based on different similarity calculations, thus providing recommendations that do not necessarily overlap. -%% - Brief description of what it is and what it does -%% - Architecture (with a nice diagram) [Alo, can you make this in Omnigraffle? I can then adjust/refine] -%% - More details about individual components we use (Yago, musicbrainz, sameas, dbpedia etc.) -%% - Brief intro to components we developed for artist similarity (just to bridge to Section 4) \section{Artist similarity} -%% 4. Artist similarity -%% 4.1 Socio-cultiral linkage (using linked data) -%% 4.2 Artist similarity by NLP [needs a better subtitle] -%% 4.3 Artist similarity by features [i can write this part] Music does not lend itself easily to categorisation. There are many ways in which artist can be, and in fact are, considered to be related. Similarity may refer to whether artists' songs sound similar, or are perceived to be in the same style or genre. But it may also mean that they are followed by people from similar social backgrounds or political inclinations, or similar ages; or perhaps they are similar because they have played together, or participated in the same event, or their songs touch on similar themes. Linked data facilitates faceted searching and displaying of information\cite{Oren2006}: an artist may be similar to many other artists in one of the ways just mentioned, and to a completely different plethora of artists in other senses, all of which might contribute to music discovery. Semantic web technologies can help us gather different facets of data and shape them into representations of knowledge. MusicWeb does this by searching similarities in three different domains: socio-cultural, research and journalistic literature and content-based linkage. \subsection{Socio-cultural linkage} Socio-cultural connections between artists in MusicWeb are primarily derived from YAGO categories that are incorporated into entities in DBpedia. Many categories, in particular those that can be considered extra-musical or tangential to music, that emerge as users browse MusicWeb, stem from the particular methodology used to derive YAGO information from Wikipedia. While DBpedia extracts knowledge from the same source, YAGO leverages Wikipedia category pages to link entities without adapting the Wikipedia taxonomy of these categories. The hierarchy is created by adapting the Wikipedia categories to the WordNet concept structure. This enables linking each artist to other similar artists by various commonalities such as style, geographical location, instrumentation, record label as well as more obscure categories, for example, artists who have received the same award, have shared the same fate, or belonged to the same organisation or religion. YAGO categories can reveal connections between artists that traditional isolated music datasets would not be able to establish. For example, MusicWeb links Alice Coltrane to John McLaughlin as both artists are converts to Hinduism, or Ella Fitzgerald to Jerry Garcia because both belong to the category of American amputees, or further still, the guitarist of heavy metal band Pantera to South African singer and civil rights activist Miriam Makeba as both died on stage. -% NOTE: not sure about this. Do we consider the dbpedia queries to be socio-cultural? or the collaborates-with in musicbrainz? Or do you (George) mean something like the introduction just above? + \subsection{Literature-based linking} -Often artist share a connection through literature topics. For example: a psychologist interested in self-image during adolescence might want to research the impact of artists like Miley Cyrus or Rihanna on young teenagers\cite{Lamb2013}. Or a historian researching class politics in the UK might write about The Sex Pistols and John Lennon\cite{Moliterno2012}. In order to extract these relations one must mine the data from texts using natural language processing. Our starting point is a large database of 100,000 artists. MusicWeb searches several sources and collects texts that mention each artist. It then carries out semantic analysis to identify connections between artists and higher-level topics. There are two main sources of texts: +Often artists share a connection through literature topics. For example: a psychologist interested in self-image during adolescence might want to research the impact of artists like Miley Cyrus or Rihanna on young teenagers\cite{Lamb2013}. Or a historian researching class politics in the UK might write about The Sex Pistols and John Lennon\cite{Moliterno2012}. In order to extract these relations one must mine the data from texts using natural language processing. Our starting point is a large database of 100,000 artists. MusicWeb searches several sources and collects texts that mention each artist. It then carries out semantic analysis to identify connections between artists and higher-level topics. There are two main sources of texts: \begin{enumerate} \item Research articles. There are various web resources that allow querying their research literature databases. MusicWeb uses Mendeley\footnote{\url{http://dev.mendeley.com/}} and Elsevier\footnote{\url{http://dev.elsevier.com/}}. Both resources offer managed and largely curated data and search possibilities include keywords, authors and disciplines. Data comprehension varies, but most often it features an array of keywords, an abstract, readership categorised according to discipline and sometimes the article itself. \item Online publications, such as newspapers, music magazines and blogs focused on music. This is non-managed, non-curated data, it must be extracted from the body of the text. The data is accessed after having crawled websites searching for keywords or tags in the title, and then scraped. External links contained in the page are also followed. @@ -289,7 +269,7 @@ \subsection{Content-based linking}\label{sec:mir} -Content-based Music Information Retrieval (MIR) \cite{casey08} facilitates applications that rely on perceptual, statistical, semantic or musical features derived from audio using digital signal processing and machine learning methods. These features may include statistical aggregates computed from time-frequency representations extracted over short time windows. For instance, spectral centroid is said to correlate with the perceived brightness of a sound \cite{Schubert:06}, therefore it may be used in the characterisation in timbral similarity between music pieces. More complex representations include features that are extracted using a perceptually motivated algorithm. Mel-Frequency Cepstral Coefficients (MFCCs) for instance are often used in speech recognition as well as in estimating music similarity \cite{logan2000mel}. Higher-level musical features include keys, chords, tempo, rhythm, as well as semantic features like genre or mood, with specific algorithms to extract this information from audio. +Content-based Music Information Retrieval (MIR) \cite{casey08} facilitates applications that rely on perceptual, statistical, semantic or musical features derived from audio using digital signal processing and machine learning methods. These features may include statistical aggregates computed from time-frequency representations extracted over short time windows. For instance, spectral centroid is said to correlate with the perceived brightness of a sound \cite{Schubert:06}, therefore it may be used in the characterisation in timbral similarity between music pieces. More complex representations include features that are extracted using a perceptually motivated algorithm. Mel-Frequency Cepstral Coefficients (MFCCs) for instance are often used in speech recognition as well as in estimating music similarity \cite{logan2000mel}. Higher-level musical features include keys, chords, tempo, rhythm, as well as semantic features like genre or mood, with specific algorithms to extract this information from audio. % Content-based features are increasingly used in music recommendation systems to overcome issues such as infrequent access of lesser known pieces in large music catalogues (the ``long tail'' problem) or the difficulty of recommending new pieces without user ratings in systems that employ collaborative filtering (``cold start'' problem) \cite{Celma2010}. @@ -298,9 +278,9 @@ High-level stylistic descriptors are not easily estimated from audio but they can correlate with lower level features such as the average tempo of a track, the frequency of note onsets, the most commonly occurring keys or chords or the overall spectral envelope that characterises dominant voices or instrumentation. To exploit different types of similarity, we model each artist using three main categories of audio descriptors: rhythmic, harmonic and timbral. We compute the joint distribution of several low-level features in each category over a large collection of tracks from each artist. We then link artists exhibiting similar distributions of these features. % for XXXX artists with a mean track count of YYY -We obtain audio features form the AcousticBrainz\footnote{https://acousticbrainz.org/} Web service which provides descriptors in each category of interest. Tracks are indexed by MusicBrainz identifiers enabling unambiguous linking to artists and other relevant metadata. For each artist in our database, we retrieve features for a large collection of their tracks in the above categories, including beats-per-minute and onset rate (rhythmic), chord histograms (harmonic) and MFCC (timbral) features. +We obtain audio features form the AcousticBrainz\footnote{https://acousticbrainz.org/} Web service which provides audio descriptors in each category of interest. Tracks are indexed by MusicBrainz identifiers enabling unambiguous linking to artists and other relevant metadata. For each artist in our database, we retrieve features for a large collection of their tracks in the above categories, including beats-per-minute and onset rate (rhythmic), chord histograms (harmonic) and MFCC (timbral) features. -For each artist, we fit a Gaussian Mixture Model (GMM) with full covariances on each set of aggregated features in each category across several tracks and compute pair-wise distances $D_{cat}$ within the selected category using Eq.\ref{eq:dist} +For each artist, we fit a Gaussian Mixture Model (GMM) with full covariances on each set of aggregated features in each category across several tracks and compute the distances $D_{cat}$ for the selected category using Eq.\ref{eq:dist} % \begin{equation}\label{eq:dist} D_{cat} = d_{skl}(artist\_model_{cat}(i), artist\_model_{cat}(j)), @@ -371,129 +351,7 @@ \end{enumerate} \end{itemize} - % - % ---- Bibliography ---- - % - %% \vspace{-1em}\begin{thebibliography}{5} - %% % - - - %% \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{Aucoutourier2002} - %% J. J.~Aucouturier and F~Pachet. - %% \newblock Music Similarity Measures: What is the Use. - %% \newblock In {\em Proceedings 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{Celma2010} - %% \`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{Zhou2004} - %% S.~Zhou and R. J.~Mondrag\'on - %% \newblock The rich-club phenomenon in the Internet topology - %% \newblock In {\em Communications Letters, IEEE}, 2004 - - %% \bibitem{Lee2015} - %% J. H.~Lee and R.~Price - %% \newblock Understanding users of commercial music services through personas: design implications. - %% \newblock In {\em Proceedings of the 16th ISMIR Conference}, M\'alaga, Spain, 2015 - - %% \bibitem{Jennings2007} - %% D.~Jennings. - %% \newblock Net, Blogs and Rock ’n’ Rolls: How Digital Discovery Works and What It Means for Consumers. - %% \newblock Nicholas Brealey Pub., 2007 - - - %% \bibitem{Pachet2005} - %% F.~Pachet - %% \newblock Knowledge management and musical metadata. - %% \newblock In {\em Encyclopedia of Knowledge Management}, Schwartz, D. Ed. Idea Group, 2005 - - - %% \bibitem{Marchioni2006} - %% G.~Marchionini - %% \newblock Exploratory search: from finding to understanding. - %% \newblock In {\em COMMUNICATIONS OF THE ACM}, 49(9), 2006 - - %% \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. - - %% \bibitem{Porter:ISMIR:15} - %% A.~Porter, D.~Bogdanov, R.~Kaye, R.~Tsukanov, and X.~Serra. - %% \newblock Acousticbrainz: a community platform for gathering music information - %% obtained from audio. - %% \newblock In {\em 16th International Society for Music Information Retrieval - %% (ISMIR) Conference}, 2015. - - %% \bibitem{DBLP:conf/ismir/RaimondASG07} - %% Y~Raimond, S.~Abdallah, M.~Sandler, and F.~Giasson. - %% \newblock The music ontology. - %% \newblock In {\em Proceedings of the 8th International Conference on Music - %% Information Retrieval, ISMIR 2007, Vienna, Austria, September 23-27}, 2007. - - %% \bibitem{Suchanek:WWW:2007} - %% F.~Suchanek, G.~Kasneci, and G.~Weikum - %% \newblock YAGO: A Core of Semantic Knowledge Unifying WordNet and Wikipedia. - %% \newblock In {\em Proceedings of the 16th international World Wide Web conference, May 8–12, 2007, Banff, Alberta, Canada.}, 2007. - - %% \bibitem{Oren2006} - %% E.~Oren, R.~ Delbru, and S.~Decker - %% \newblock Extending faceted navigation for rdf data. - %% \newblock In {\em ISWC, 559–572}, 2006 - - %% \bibitem{Lamb2013} - %% S.~Lamb, K.~Graling and E. E. Wheeler - %% \newblock ‘Pole-arized’ discourse: An analysis of responses to Miley Cyrus’s Teen Choice Awards pole dance. - %% \newblock In {\em Feminism Psychology vol. 23}, May 2013 - - %% \bibitem{Moliterno2012} - %% A. G.~Moliterno - %% \newblock What Riot? Punk Rock Politics, Fascism, and Rock Against Racism. - %% \newblock Published online: \url{http://www.studentpulse.com/articles/612/what-riot-punk-rock-politics-fascism-and-rock-against-racism}, 2012 - - %% \bibitem{Manning1999} - %% C.~Manning and H.~Sch\"utze - %% \newblock Foundations of Statistical Natural Language Processing. - %% \newblock MIT Press, Cambridge, MA., 1999 - - - %% \bibitem{Wong2012} - %% W.~Wong, W.~Liu and M.~Bennamoun - %% \newblock Ontology Learning from Text: A Look Back and into the Future - %% \newblock In {\em ACM Comput. Surv. 44, 4}, 2012 - - - %% \bibitem{Landauer1998} - %% T.~Landauer, P.~Folt, and D.~Laham. - %% \newblock An introduction to latent semantic analysis - %% \newblock In {\em Discourse processes, 25}, 1998 - - %% \bibitem{Blei2012} - %% D.~Blei, A.~ Ng, and M.I.~Jordan. - %% \newblock Latent Dirichlet Allocation. - %% \newblock In {\em Journal of Machine Learning Research, 3(4-5), 993–1022}, 2012 - - - %% \end{thebibliography} - - \bibliographystyle{plain} - \bibliography{musicweb} + \bibliographystyle{plain} + \bibliography{musicweb} \end{document}