{"id":"https://openalex.org/W4393649914","doi":"https://doi.org/10.5281/zenodo.10223363","title":"WikiMuTe: A web-sourced dataset of semantic descriptions for music audio","display_name":"WikiMuTe: A web-sourced dataset of semantic descriptions for music audio","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4393649914","doi":"https://doi.org/10.5281/zenodo.10223363"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:10223363","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10223363","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"type":"dataset","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10223363","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038446032","display_name":"Benno Weck","orcid":"https://orcid.org/0000-0002-5760-6922"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Weck, Benno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074883610","display_name":"Holger Kirchhoff","orcid":"https://orcid.org/0009-0008-4655-729X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kirchhoff, Holger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078194825","display_name":"Peter Grosche","orcid":"https://orcid.org/0000-0002-5525-5233"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grosche, Peter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier, Serra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038446032"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13996","display_name":"Diverse Musicological Studies","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6546890735626221},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.48977112770080566},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.42757901549339294},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40132343769073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6546890735626221},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48977112770080566},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.42757901549339294},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40132343769073486}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:zenodo.org:10223363","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10223363","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:10223363","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10223363","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2333894209","https://openalex.org/W65665365","https://openalex.org/W2031517545","https://openalex.org/W4234878310","https://openalex.org/W2182204580"],"abstract_inverted_index":{"<p>This":[0],"upload":[1],"contains":[2,21,176,185,192,203,344],"the":[3,14,43,47,54,167,174,178,186,193,197,204,207,210,213,216,220,225,232,235,242,245,248,251,254,258,272,342,349,352],"supplementary":[4],"material":[5],"for":[6,25,40,148,284],"our":[7],"<a":[8,15],"href=\"https://arxiv.org/abs/2312.09207\"":[9],"target=\"_blank\"":[10,17,57,76,98,116,151,330],"rel=\"noopener\">paper</a>":[11],"presented":[12],"at":[13,72],"href=\"https://mmm2024.org/\"":[16],"rel=\"noopener\">MMM2024":[18],"conference</a>.</p>\\n<h2>Dataset</h2>\\n<p>The":[19],"dataset":[20,168,266,343],"rich":[22],"text":[23,221,259,353],"descriptions":[24],"music":[26],"audio":[27,33,211,249],"files":[28,34],"collected":[29,223,230,240,261,356],"from":[30,231,241],"Wikipedia":[31,217,233,243,255],"articles.</p>\\n<p>The":[32],"are":[35,171],"freely":[36],"accessible":[37],"and":[38,142,291,294,297],"available":[39,326],"download":[41],"through":[42],"URLs":[44],"provided":[45],"in":[46,82,169,173,267,341],"dataset.</p>\\n<h3>Example</h3>\\n<p>A":[48],"few":[49],"hand-picked,":[50],"simplified":[51],"examples":[52],"of":[53,66,79,166,209,215,247,253,281],"dataset. </p>\\n<table>\\n<tbody>\\n<tr>\\n<td>\\n<p><strong>file</strong></p>\\n</td>\\n<td>\\n<p><strong>aspects</strong></p>\\n</td>\\n<td>\\n<p><strong>sentences</strong></p>\\n</td>\\n</tr>\\n<tr>\\n<td>\\n<p><a":[55],"href=\"https://upload.wikimedia.org/wikipedia/commons/7/7a/Bongo_sound.wav\"":[56],"rel=\"noopener\"><strong>\ud83d\udd08":[58,77,99,117,152],"Bongo":[59],"sound.wav</strong></a></p>\\n</td>\\n<td>\\n<p>['bongoes',":[60],"'percussion":[61],"instrument',":[62,129],"'cumbia',":[63],"'drums']</p>\\n</td>\\n<td>\\n<p>['a":[64,94],"loop":[65],"bongoes":[67],"playing":[68],"a":[69,83,108,131,345],"cumbia":[70],"beat":[71],"99":[73],"bpm']</p>\\n</td>\\n</tr>\\n<tr>\\n<td>\\n<p><a":[74],"href=\"https://upload.wikimedia.org/wikipedia/commons/4/46/Example_of_double_tracking_in_a_pop-rock_song_%283_guitar_tracks%29.ogg\"":[75],"Example":[78],"double":[80],"tracking":[81],"pop-rock":[84,95],"song":[85],"(3":[86],"guitar":[87],"tracks).ogg</strong></a></p>\\n</td>\\n<td>\\n<p>['bass',":[88],"'rock',":[89],"'guitar":[90],"music',":[91,104],"'guitar',":[92],"'pop',":[93],"song']</p>\\n</td>\\n</tr>\\n<tr>\\n<td>\\n<p><a":[96],"href=\"https://upload.wikimedia.org/wikipedia/commons/6/62/OriginalDixielandJassBand-JazzMeBlues.ogg\"":[97],"OriginalDixielandJassBand-JazzMeBlues.ogg</strong></a></p>\\n</td>\\n<td>\\n<p>['jazz":[100],"standard',":[101,110],"'instrumental',":[102],"'jazz":[103],"'jazz']</p>\\n</td>\\n<td>\\n<p>['Considered":[105],"to":[106,348],"be":[107],"jazz":[109,113],"'is":[111],"an":[112],"composition']</p>\\n</td>\\n</tr>\\n<tr>\\n<td>\\n<p><a":[114],"href=\"https://upload.wikimedia.org/wikipedia/commons/5/58/Colin_Ross_-_Etherea.ogg\"":[115],"Colin":[118],"Ross":[119],"-":[120],"Etherea.ogg</strong></a></p>\\n</td>\\n<td>\\n<p>['chirping":[121],"birds',":[122,144],"'ambient":[123],"percussion',":[124],"'new-age',":[125],"'flute',":[126],"'recorder',":[127],"'single":[128],"'woodwind']</p>\\n</td>\\n<td>\\n<p>['features":[130],"single":[132],"instrument":[133],"with":[134],"delayed":[135],"echo,":[136],"as":[137,139],"well":[138],"ambient":[140],"percussion":[141],"chirping":[143],"'a":[145],"new-age":[146],"composition":[147],"recorder']</p>\\n</td>\\n</tr>\\n<tr>\\n<td>\\n<p><a":[149],"href=\"https://upload.wikimedia.org/wikipedia/commons/8/8b/Belau_rekid_%28instrumental%29.oga\"":[150],"Belau":[153],"rekid":[154],"(instrumental).oga</strong></a></p>\\n</td>\\n<td>\\n<p>['instrumental',":[155],"'brass":[156],"band']</p>\\n</td>\\n<td>\\n<p>['an":[157],"instrumental":[158],"brass":[159],"band":[160],"performance']</p>\\n</td>\\n</tr>\\n<tr>\\n<td>\\n<p><strong>...</strong></p>\\n</td>\\n<td>\\n<p>...</p>\\n</td>\\n<td>\\n<p>...</p>\\n</td>\\n</tr>\\n</tbody>\\n</table>\\n<h3>Dataset":[161],"structure</h3>\\n<p>We":[162],"provide":[163],"three":[164],"variants":[165],"the <code>data</code> folder.</p>\\n<p>All":[170],"described":[172],"paper.</p>\\n<ol>\\n<li><code>all.csv</code>":[175],"all":[177],"data":[179,187,194,324,354],"we":[180],"collected,":[181],"without":[182],"any":[183],"filtering.</li>\\n<li><code>filtered_sf.csv</code>":[184],"obtained":[188,195],"using":[189,196],"the <em>self-filtering</em>":[190],"method.</li>\\n<li><code>filtered_mc.csv</code>":[191],"<em>MusicCaps</em> dataset":[198],"method.</li>\\n</ol>\\n<h3>File":[199],"structure</h3>\\n<p>Each":[200],"CSV":[201],"file":[202],"following":[205,273],"columns:</p>\\n<ul>\\n<li><code>file</code>:":[206],"name":[208],"file</li>\\n<li><code>pageid</code>:":[212],"ID":[214],"article":[218,256],"where":[219,257,351],"was":[222,260,355],"from</li>\\n<li><code>aspects</code>:":[224],"short-form":[226],"(tag)":[227],"description":[228,238],"texts":[229,239],"articles</li>\\n<li><code>sentences</code>:":[234],"long-form":[236],"(caption)":[237],"articles</li>\\n<li><code>audio_url</code>:":[244],"URL":[246,252,346],"file</li>\\n<li><code>url</code>:":[250],"from</li>\\n</ul>\\n<h3>Citation</h3>\\n<div>\\n<p>If":[262],"you":[263],"use":[264],"this":[265],"your":[268],"research,":[269],"please":[270],"cite":[271],"paper:</p>\\n<div>\\n<pre><code>@inproceedings{wikimute,</code><br><code>":[274],"title":[275],"=":[276,288,301,305,308,313,316,319,322],"{WikiMuTe:":[277],"{A}":[278],"Web-Sourced":[279],"Dataset":[280],"Semantic":[282],"Descriptions":[283],"Music":[285],"Audio},</code><br><code>":[286],"author":[287],"{Weck,":[289],"Benno":[290],"Kirchhoff,":[292],"Holger":[293],"Grosche,":[295],"Peter":[296],"Serra,":[298],"Xavier},</code><br><code>":[299],"booktitle":[300],"\"MultiMedia":[302],"Modeling\",</code><br><code>":[303],"year":[304],"\"2024\",</code><br><code>":[306],"publisher":[307],"\"Springer":[309],"Nature":[310],"Switzerland\",</code><br><code>":[311],"address":[312],"\"Cham\",</code><br><code>":[314],"pages":[315],"\"42--56\",</code><br><code>":[317],"doi":[318],"{10.1007/978-3-031-56435-2_4},</code><br><code>":[320],"url":[321],"{https://doi.org/10.1007/978-3-031-56435-2_4},</code><br><code>}</code></pre>\\n</div>\\n</div>\\n<h3>License</h3>\\n<p>The":[323],"is":[325],"under":[327],"the <a":[328],"href=\"https://creativecommons.org/licenses/by-sa/3.0/\"":[329],"rel=\"noopener\">Creative":[331],"Commons":[332],"Attribution-ShareAlike":[333],"3.0":[334],"Unported":[335],"(CC":[336],"BY-SA":[337],"3.0)":[338],"license</a>.</p>\\n<p>Each":[339],"entry":[340],"linking":[347],"article,":[350],"from.</p>":[357]},"counts_by_year":[],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}