{"_id":"fbMLi49TBHkSQM94H","bibbaseid":"levy-sandler-musicinformationretrievalusingsocialtagsandaudio-2009","author_short":["Levy, M.","Sandler, M."],"bibdata":{"bibtype":"article","type":"article","title":"Music Information Retrieval Using Social Tags and Audio","volume":"11","issn":"1520-9210","doi":"10.1109/TMM.2009.2012913","abstract":"In this paper we describe a novel approach to applying text-based information retrieval techniques to music collections. We represent tracks with a joint vocabulary consisting of both conventional words, drawn from social tags, and audio muswords, representing characteristics of automatically-identified regions of interest within the signal. We build vector space and latent aspect models indexing words and muswords for a collection of tracks, and show experimentally that retrieval with these models is extremely well-behaved. We find in particular that retrieval performance remains good for tracks by artists unseen by our models in training , and even if tags for their tracks are extremely sparse.","number":"3","journal":"Ieee Transactions on Multimedia","author":[{"propositions":[],"lastnames":["Levy"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Sandler"],"firstnames":["M."],"suffixes":[]}],"year":"2009","keywords":"#nosource","pages":"383–395","bibtex":"@article{levy_music_2009,\n\ttitle = {Music {Information} {Retrieval} {Using} {Social} {Tags} and {Audio}},\n\tvolume = {11},\n\tissn = {1520-9210},\n\tdoi = {10.1109/TMM.2009.2012913},\n\tabstract = {In this paper we describe a novel approach to applying text-based information retrieval techniques to music collections. We represent tracks with a joint vocabulary consisting of both conventional words, drawn from social tags, and audio muswords, representing characteristics of automatically-identified regions of interest within the signal. We build vector space and latent aspect models indexing words and muswords for a collection of tracks, and show experimentally that retrieval with these models is extremely well-behaved. We find in particular that retrieval performance remains good for tracks by artists unseen by our models in training , and even if tags for their tracks are extremely sparse.},\n\tnumber = {3},\n\tjournal = {Ieee Transactions on Multimedia},\n\tauthor = {Levy, M. and Sandler, M.},\n\tyear = {2009},\n\tkeywords = {\\#nosource},\n\tpages = {383--395},\n}\n\n","author_short":["Levy, M.","Sandler, M."],"key":"levy_music_2009","id":"levy_music_2009","bibbaseid":"levy-sandler-musicinformationretrievalusingsocialtagsandaudio-2009","role":"author","urls":{},"keyword":["#nosource"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/fsimonetta","dataSources":["pzyFFGWvxG2bs63zP"],"keywords":["#nosource"],"search_terms":["music","information","retrieval","using","social","tags","audio","levy","sandler"],"title":"Music Information Retrieval Using Social Tags and Audio","year":2009}