{"id":"https://openalex.org/W4409201595","doi":"https://doi.org/10.1587/transinf.2024edl8096","title":"Spectral-Domain Augmentation for Cover Song Identification","display_name":"Spectral-Domain Augmentation for Cover Song Identification","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4409201595","doi":"https://doi.org/10.1587/transinf.2024edl8096"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2024edl8096","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8096","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8096/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8096/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010137230","display_name":"Jinsoo Seo","orcid":"https://orcid.org/0000-0001-6432-6964"},"institutions":[{"id":"https://openalex.org/I133533813","display_name":"Gangneung\u2013Wonju National University","ror":"https://ror.org/0461cvh40","country_code":"KR","type":"education","lineage":["https://openalex.org/I133533813"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jinsoo SEO","raw_affiliation_strings":["Department of Electrical Engineering, Gangneung-Wonju National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Gangneung-Wonju National University","institution_ids":["https://openalex.org/I133533813"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010137230"],"corresponding_institution_ids":["https://openalex.org/I133533813"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06232427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E108.D","issue":"10","first_page":"1287","last_page":"1291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9916999936103821,"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":0.9916999936103821,"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":0.9835000038146973,"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":0.9549000263214111,"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/computer-science","display_name":"Computer science","score":0.7746239900588989},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.6619681119918823},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6426085829734802},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5115021467208862},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3535923361778259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3283531665802002},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07057583332061768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746239900588989},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.6619681119918823},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6426085829734802},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5115021467208862},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3535923361778259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3283531665802002},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07057583332061768},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2024edl8096","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8096","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8096/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2024edl8096","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8096","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8096/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409201595.pdf","grobid_xml":"https://content.openalex.org/works/W4409201595.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2154473523","https://openalex.org/W2191779130","https://openalex.org/W2509065397","https://openalex.org/W2896276533","https://openalex.org/W2936774411","https://openalex.org/W2954996726","https://openalex.org/W2985214749","https://openalex.org/W3015271757","https://openalex.org/W3015611708","https://openalex.org/W3015666964","https://openalex.org/W3094833745","https://openalex.org/W3208228585","https://openalex.org/W4224920338","https://openalex.org/W4390463217"],"related_works":["https://openalex.org/W4232403550","https://openalex.org/W623607250","https://openalex.org/W4245429118","https://openalex.org/W4205110281","https://openalex.org/W4212927854","https://openalex.org/W4211151614","https://openalex.org/W4244798043","https://openalex.org/W4361866086","https://openalex.org/W4251969024","https://openalex.org/W4250793136"],"abstract_inverted_index":{"In":[0],"many":[1],"applications,":[2],"data":[3,47],"imbalance":[4],"and":[5,68,78],"annotation":[6],"challenges":[7],"limit":[8],"the":[9,15,75,89,100,104,108,115],"size":[10],"of":[11,17,110,117],"training":[12,37],"datasets,":[13],"hindering":[14],"ability":[16],"deep":[18],"neural":[19,118],"networks":[20,119],"to":[21,113],"fully":[22],"leverage":[23],"their":[24,80],"representational":[25],"capacity.":[26],"Data":[27],"augmentation":[28,48,58,90],"is":[29],"a":[30,93],"widely":[31],"used":[32],"countermeasure":[33],"that":[34],"generates":[35],"additional":[36],"samples":[38],"by":[39],"manipulating":[40],"existing":[41],"data.":[42],"This":[43],"paper":[44],"investigates":[45],"spectral-domain":[46],"methods":[49,91],"specifically":[50],"for":[51,120],"cover":[52,84,121],"song":[53,85,122],"identification":[54,86],"task,":[55],"enabling":[56],"on-the-fly":[57],"with":[59],"minimal":[60],"computational":[61],"overhead.":[62],"We":[63],"explore":[64],"various":[65],"spectral":[66,101,111],"modifications":[67],"mixing":[69,94],"techniques,":[70],"applying":[71],"them":[72],"directly":[73],"in":[74,99],"frequency":[76],"domain,":[77],"evaluate":[79],"effectiveness":[81],"on":[82],"two":[83],"datasets.":[87],"Among":[88],"tested,":[92],"approach":[95],"involving":[96],"cut-and-paste":[97],"operations":[98],"domain":[102],"achieved":[103],"highest":[105],"accuracy,":[106],"demonstrating":[107],"potential":[109],"augmentations":[112],"enhance":[114],"performance":[116],"identification.":[123]},"counts_by_year":[],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}
