{"id":"https://openalex.org/W4295336532","doi":"https://doi.org/10.48550/arxiv.2203.13422","title":"Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic Music","display_name":"Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic Music","publication_year":2022,"publication_date":"2022-03-25","ids":{"openalex":"https://openalex.org/W4295336532","doi":"https://doi.org/10.48550/arxiv.2203.13422"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2203.13422","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.13422","pdf_url":"https://arxiv.org/pdf/2203.13422","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.13422","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088397456","display_name":"Sangeun Kum","orcid":"https://orcid.org/0000-0001-9305-7281","observed_orcids":["https://orcid.org/0000-0001-9305-7281"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kum, Sangeun","raw_affiliation_strings":["Neutune Research , Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neutune Research , Seoul , South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049268304","display_name":"Jongpil Lee","orcid":"https://orcid.org/0000-0002-1126-0081","observed_orcids":["https://orcid.org/0000-0002-1126-0081"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jongpil","raw_affiliation_strings":["Neutune Research , Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neutune Research , Seoul , South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006810361","display_name":"Keunhyoung Luke Kim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Keunhyoung Luke","raw_affiliation_strings":["Neutune Research , Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neutune Research , Seoul , South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101869298","display_name":"Taehyoung Kim","orcid":"https://orcid.org/0000-0001-6557-1371","observed_orcids":["https://orcid.org/0000-0001-6557-1371"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Taehyoung","raw_affiliation_strings":["Neutune Research , Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neutune Research , Seoul , South Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119","observed_orcids":["https://orcid.org/0000-0003-2664-2119"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam, Juhan","raw_affiliation_strings":["Graduate School of Culture Technology , KAIST , Daejeon , South Korea","Neutune Research , Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology , KAIST , Daejeon , South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Neutune Research , Seoul , South Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":1.0,"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":1.0,"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/T11349","display_name":"Music Technology and Sound Studies","score":9.999999747378752e-05,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0,"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/polyphony","display_name":"polyphony","score":0.9890000224113464},{"id":"https://openalex.org/keywords/teacher-student-models","display_name":"teacher-student models","score":0.8840000033378601},{"id":"https://openalex.org/keywords/self-training","display_name":"self-training","score":0.9179999828338623}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8133334517478943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322583794593811},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7121874094009399},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6986756920814514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5978823304176331},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5732258558273315},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.43022167682647705},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4244469404220581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3698950409889221},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1805773675441742},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09592300653457642},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0799451470375061},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2203.13422","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.13422","pdf_url":"https://arxiv.org/pdf/2203.13422","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2203.13422","doi":"https://doi.org/10.48550/arxiv.2203.13422","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.13422","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.13422","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.13422","pdf_url":"https://arxiv.org/pdf/2203.13422","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4295336532.pdf","grobid_xml":"https://content.openalex.org/works/W4295336532.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2580221632","https://openalex.org/W2971458685"],"related_works":["https://openalex.org/W4392909491","https://openalex.org/W4392730530","https://openalex.org/W4372260560","https://openalex.org/W3096787185","https://openalex.org/W3130253270","https://openalex.org/W3160649916","https://openalex.org/W4226266814","https://openalex.org/W7160538497","https://openalex.org/W4311187172","https://openalex.org/W4311167650"],"abstract_inverted_index":{"Lack":[0],"of":[1,83,89],"large-scale":[2,103],"note-level":[3,42],"labeled":[4,141,152],"data":[5,106,128,142],"is":[6],"the":[7,18,37,53,64,87,97,110,122,136,147],"major":[8],"obstacle":[9],"to":[10,41,115,132],"singing":[11],"transcription":[12],"from":[13,24],"polyphonic":[14],"music.":[15],"We":[16],"address":[17],"issue":[19],"by":[20,71],"using":[21],"pseudo":[22,39],"labels":[23,40],"vocal":[25,74],"pitch":[26,44,75],"estimation":[27,76],"models":[28,77],"given":[29],"unlabeled":[30,104,127],"data.":[31,153],"The":[32,93],"proposed":[33,98],"method":[34,99],"first":[35],"converts":[36],"frame-level":[38],"through":[43,56],"and":[45,86,107,135],"rhythm":[46],"quantization":[47],"steps.":[48],"Then,":[49],"it":[50],"further":[51],"improves":[52],"label":[54],"quality":[55],"self-training":[57,108],"in":[58,91],"a":[59],"teacher-student":[60,84],"framework.":[61],"To":[62],"validate":[63],"method,":[65],"we":[66,119],"conduct":[67],"various":[68],"experiment":[69],"settings":[70],"investigating":[72],"two":[73,81],"as":[78],"pseudo-label":[79],"generators,":[80],"setups":[82],"frameworks,":[85],"number":[88],"iterations":[90],"self-training.":[92],"results":[94],"show":[95,120],"that":[96,121],"can":[100],"effectively":[101],"leverage":[102],"audio":[105],"with":[109,125,139,150],"noisy":[111],"student":[112],"model":[113,123,137,148],"helps":[114],"improve":[116],"performance.":[117],"Finally,":[118],"trained":[124,138,149],"only":[126,151],"has":[129],"comparable":[130],"performance":[131],"previous":[133],"works":[134],"additional":[140],"achieves":[143],"higher":[144],"accuracy":[145],"than":[146]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-09-13T00:00:00"}
