{"id":"https://openalex.org/W4416017203","doi":"https://doi.org/10.1145/3746252.3761614","title":"S2Cap: A Benchmark and a Baseline for Singing Style Captioning","display_name":"S2Cap: A Benchmark and a Baseline for Singing Style Captioning","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017203","doi":"https://doi.org/10.1145/3746252.3761614"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761614","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761614","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3761614","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081750602","display_name":"Hyunjong Ok","orcid":"https://orcid.org/0009-0003-7204-7350"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyunjong Ok","raw_affiliation_strings":["Pohang University of Science and Technology, Pohang, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102980072","display_name":"Jaeho Lee","orcid":"https://orcid.org/0000-0002-1349-8595"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeho Lee","raw_affiliation_strings":["Pohang University of Science and Technology, Pohang, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081750602"],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43940587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6492","last_page":"6497"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.795799970626831,"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":0.795799970626831,"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/T10863","display_name":"Voice and Speech Disorders","score":0.06310000270605087,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.052299998700618744,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/singing","display_name":"Singing","score":0.9391000270843506},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.8378000259399414},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6955000162124634},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6632999777793884},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6184999942779541},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5321999788284302}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9391000270843506},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.8378000259399414},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6955000162124634},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6632999777793884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6373999714851379},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6184999942779541},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5206999778747559},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36390000581741333},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2653000056743622}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761614","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761614","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746252.3761614","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761614","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2067709094","https://openalex.org/W2101105183","https://openalex.org/W2185175083","https://openalex.org/W2425121537","https://openalex.org/W2886641317","https://openalex.org/W2914699769","https://openalex.org/W2949376505","https://openalex.org/W2970641574","https://openalex.org/W3015591594","https://openalex.org/W3016243847","https://openalex.org/W3160173020","https://openalex.org/W3205860970","https://openalex.org/W4285345683","https://openalex.org/W4372260250","https://openalex.org/W4372340819","https://openalex.org/W4375869156","https://openalex.org/W4375928773","https://openalex.org/W4391021679","https://openalex.org/W4392903591","https://openalex.org/W4392903700","https://openalex.org/W4393160753","https://openalex.org/W4401042666","https://openalex.org/W4402112231","https://openalex.org/W4403780871"],"related_works":[],"abstract_inverted_index":{"Singing":[0],"voices":[1,22,64],"contain":[2],"much":[3],"richer":[4],"information":[5],"than":[6],"common":[7],"voices,":[8],"including":[9],"varied":[10],"vocal":[11],"and":[12,30,57,72,82],"acoustic":[13,32],"properties.":[14],"However,":[15],"current":[16],"open-source":[17],"audio-text":[18],"datasets":[19],"for":[20,86],"singing":[21,53,63,87],"capture":[23],"only":[24],"a":[25,60],"narrow":[26],"range":[27],"of":[28,62],"attributes":[29],"lack":[31],"features,":[33],"leading":[34],"to":[35],"limited":[36],"utility":[37],"towards":[38],"downstream":[39],"tasks,":[40],"such":[41],"as":[42],"style":[43,54,88],"captioning.":[44,89],"To":[45],"fill":[46],"this":[47,76],"gap,":[48],"we":[49,78],"formally":[50],"define":[51],"the":[52],"captioning":[55],"task":[56],"present":[58],"S2Cap,":[59],"dataset":[61,91],"with":[65],"detailed":[66],"descriptions":[67],"covering":[68],"diverse":[69],"vocal,":[70],"acoustic,":[71],"demographic":[73],"characteristics.":[74],"Using":[75],"dataset,":[77],"develop":[79],"an":[80],"efficient":[81],"straightforward":[83],"baseline":[84],"algorithm":[85],"The":[90],"is":[92],"available":[93],"at":[94],"https://zenodo.org/records/15673764.":[95]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-08T00:00:00"}
