{"id":"https://openalex.org/W6969071748","doi":"https://doi.org/10.5281/zenodo.14877383","title":"End-to-End Automatic Singing Skill Evaluation Using Cross-Attention and Data Augmentation for Solo Singing and Singing With Accompaniment","display_name":"End-to-End Automatic Singing Skill Evaluation Using Cross-Attention and Data Augmentation for Solo Singing and Singing With Accompaniment","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6969071748","doi":"https://doi.org/10.5281/zenodo.14877383"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877383","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877383","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877383","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yaolong Ju","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yaolong Ju","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chun Yat Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chun Yat Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Betty Corti\u00f1as Lorenzo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Betty Corti\u00f1as Lorenzo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiajun Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Fan Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Fan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Simon Lui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Lui","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45251098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.40130001306533813,"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":0.40130001306533813,"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/T11425","display_name":"Diverse Music Education Insights","score":0.18629999458789825,"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/T10863","display_name":"Voice and Speech Disorders","score":0.11680000275373459,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9830999970436096},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49000000953674316},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3662000000476837},{"id":"https://openalex.org/keywords/correlation-coefficient","display_name":"Correlation coefficient","score":0.3569999933242798},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.29089999198913574}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9830999970436096},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4887999892234802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46320000290870667},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32580000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877383","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877383","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877383","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877383","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6521059274673462}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"singing":[1,16,36,38,108,112],"skill":[2],"evaluation":[3],"(ASSE)":[4],"systems":[5],"are":[6],"predominantly":[7],"designed":[8],"for":[9,62,106,111],"solo":[10,35,107],"singing,":[11],"and":[12,37,87,109,121],"the":[13,73,80,125],"scenario":[14],"of":[15,104,119,129],"with":[17,39,99,113],"accompaniment":[18,40],"is":[19,48],"largely":[20],"unaddressed.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25,57],"propose":[26],"an":[27],"end-to-end":[28],"ASSE":[29],"system":[30],"that":[31,84],"effectively":[32],"processes":[33],"both":[34],"using":[41],"data":[42,53,85],"augmentation,":[43],"where":[44],"a":[45,100],"comparative":[46],"study":[47],"conducted":[49],"on":[50,79],"four":[51],"different":[52,76],"augmentation":[54,86],"approaches.":[55],"Additionally,":[56],"incorporate":[58],"bi-directional":[59],"cross-attention":[60],"(BiCA)":[61],"feature":[63],"fusion":[64],"which,":[65],"compared":[66,123],"to":[67,96,124],"simple":[68],"concatenation,":[69],"can":[70],"better":[71],"exploit":[72],"inter-relationships":[74],"between":[75],"features.":[77],"Results":[78],"10KSinging":[81],"dataset":[82],"show":[83],"BiCA":[88],"boost":[89],"performance":[90],"individually.":[91],"When":[92],"combined,":[93],"they":[94],"contribute":[95],"further":[97],"improvements,":[98],"Pearson":[101],"correlation":[102],"coefficient":[103],"0.769":[105],"0.709":[110],"accompaniment.":[114],"This":[115],"represents":[116],"relative":[117],"improvements":[118],"36.8%":[120],"26.2%":[122],"baseline":[126],"model":[127],"score":[128],"0.562,":[130],"respectively.":[131]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}