{"id":"https://openalex.org/W6929966906","doi":"https://doi.org/10.5281/zenodo.10265321","title":"On the Effectiveness of Speech Self-Supervised Learning for Music","display_name":"On the Effectiveness of Speech Self-Supervised Learning for Music","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6929966906","doi":"https://doi.org/10.5281/zenodo.10265321"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265321","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265321","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.10265321","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yinghao Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yinghao Ma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ruibin Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruibin Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yizhi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yizhi Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ge Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chenghua Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenghua Lin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xingran Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingran Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Anton Ragni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anton Ragni","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hanzhi Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanzhi Yin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Emmanouil Benetos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Norbert Gyenge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Norbert Gyenge","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ruibo Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruibo Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gus Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gus Xia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Roger B. Dannenberg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roger B. Dannenberg","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yike Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yike Guo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jie Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Fu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":15,"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":0.31544085,"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":0.9376999735832214,"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":0.9376999735832214,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.011699999682605267,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.010700000450015068,"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/task","display_name":"Task (project management)","score":0.6269999742507935},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5019999742507935},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4410000145435333},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.39969998598098755},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.36820000410079956},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34619998931884766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6827999949455261},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6269999742507935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5525000095367432},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5019999742507935},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3984000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3935999870300293},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.26809999346733093},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265321","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265321","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.10265321","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265321","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":[{"score":0.7347891330718994,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"has":[3,61],"shown":[4,46],"promising":[5],"results":[6],"in":[7,18,148],"various":[8,97],"speech":[9,55],"and":[10,77,79,85,100,168],"natural":[11],"language":[12],"processing":[13],"applications.":[14],"However,":[15,137],"its":[16],"efficacy":[17],"music":[19,33,59,67,118],"information":[20],"retrieval":[21],"(MIR)":[22],"still":[23],"remains":[24],"largely":[25],"unexplored.":[26],"While":[27],"previous":[28],"SSL":[29,56,70,91,166],"models":[30,41,57,92,129],"pre-trained":[31],"on":[32,124,153],"recordings":[34,60],"may":[35],"have":[36,45],"been":[37,62],"mostly":[38],"closed-sourced,":[39],"recent":[40],"such":[42,143],"as":[43,83],"wav2vec2.0":[44],"promise.":[47],"Nevertheless,":[48],"research":[49],"exploring":[50],"the":[51,66,103,140,154],"effectiveness":[52],"of":[53,69,142],"applying":[54],"to":[58,81],"limited.":[63],"We":[64,88],"explore":[65],"adaption":[68],"with":[71,93,107,117],"two":[72],"distinctive":[73],"speech-related":[74],"models,":[75],"data2vec1.0":[76],"Hubert,":[78],"refer":[80],"them":[82],"music2vec":[84],"musicHuBERT,":[86],"respectively.":[87],"train":[89],"12":[90],"95M":[94],"parameters":[95],"under":[96],"pre-training":[98],"configurations":[99],"systematically":[101],"evaluate":[102],"MIR":[104,110,125],"task":[105],"performances":[106],"13":[108],"different":[109],"tasks.":[111],"Our":[112],"findings":[113],"suggest":[114],"that":[115],"training":[116],"data":[119],"can":[120],"generally":[121],"improve":[122],"performance":[123],"tasks,":[126],"even":[127],"when":[128],"are":[130,159],"trained":[131],"using":[132],"paradigms":[133],"designed":[134],"for":[135,162],"speech.":[136],"we":[138],"identify":[139],"limitations":[141],"existing":[144],"speech-oriented":[145],"designs,":[146],"especially":[147],"modelling":[149],"polyphonic":[150],"information.":[151],"Based":[152],"experimental":[155],"results,":[156],"empirical":[157],"suggestions":[158],"also":[160],"given":[161],"designing":[163],"future":[164],"musical":[165],"strategies":[167],"paradigms.":[169]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}