{"id":"https://openalex.org/W3199364993","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533583","title":"Hierarchical disentangled representation learning for singing voice conversion","display_name":"Hierarchical disentangled representation learning for singing voice conversion","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3199364993","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533583","mag":"3199364993"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101589290","display_name":"Naoya Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Naoya Takahashi","raw_affiliation_strings":["R&D Center, Sony,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"R&D Center, Sony,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017387203","display_name":"Mayank Singh","orcid":"https://orcid.org/0000-0002-5350-6895"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mayank Kumar Singh","raw_affiliation_strings":["R&D Center, Sony,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"R&D Center, Sony,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["R&D Center, Sony,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"R&D Center, Sony,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101589290"],"corresponding_institution_ids":["https://openalex.org/I4210122684"],"apc_list":null,"apc_paid":null,"fwci":0.7618,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71169709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9994999766349792,"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":0.7734541893005371},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6857914328575134},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.664570689201355},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5935770869255066},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5927920341491699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5305854082107544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5136191248893738},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4806296229362488},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.4770733118057251},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3712606430053711}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734541893005371},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6857914328575134},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.664570689201355},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5935770869255066},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5927920341491699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5305854082107544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5136191248893738},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4806296229362488},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4770733118057251},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3712606430053711},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1590808459","https://openalex.org/W2067709094","https://openalex.org/W2187089797","https://openalex.org/W2294038178","https://openalex.org/W2401296648","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2752796333","https://openalex.org/W2804998325","https://openalex.org/W2902070858","https://openalex.org/W2921857201","https://openalex.org/W2946555236","https://openalex.org/W2949382160","https://openalex.org/W2962760235","https://openalex.org/W2962896155","https://openalex.org/W2963568578","https://openalex.org/W2963799213","https://openalex.org/W2971074500","https://openalex.org/W2972667718","https://openalex.org/W2972812066","https://openalex.org/W3008715487","https://openalex.org/W3016007107","https://openalex.org/W3016021263","https://openalex.org/W3016243847","https://openalex.org/W3095948607","https://openalex.org/W3104280664","https://openalex.org/W4289383906","https://openalex.org/W4294643831","https://openalex.org/W6635429420","https://openalex.org/W6697024540","https://openalex.org/W6712902469","https://openalex.org/W6745560452","https://openalex.org/W6751869084","https://openalex.org/W6755300632","https://openalex.org/W6762815247","https://openalex.org/W6762931180","https://openalex.org/W6774662120"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W2368036937"],"abstract_inverted_index":{"Conventional":[0],"singing":[1],"voice":[2],"conversion":[3],"(SVC)":[4],"methods":[5],"often":[6],"suffer":[7],"from":[8,51],"operating":[9],"in":[10,71],"high-resolution":[11],"audio":[12],"owing":[13],"to":[14,53],"a":[15,25,68],"high":[16,54],"dimensionality":[17],"of":[18,33,73],"data.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23],"propose":[24],"hierarchical":[26],"representation":[27],"learning":[28,32],"that":[29,59,65],"enables":[30],"the":[31,41,45,60],"disentangled":[34,43],"representations":[35],"with":[36,67],"multiple":[37],"resolutions":[38],"independently.":[39],"With":[40],"learned":[42],"representations,":[44],"proposed":[46,61],"method":[47,62],"progressively":[48],"performs":[49],"SVC":[50],"low":[52],"resolutions.":[55],"Experimental":[56],"results":[57],"show":[58],"outperforms":[63],"baselines":[64],"operate":[66],"single":[69],"resolution":[70],"terms":[72],"mean":[74],"opinion":[75],"score":[76],"(MOS),":[77],"similarity":[78],"score,":[79],"and":[80],"pitch":[81],"accuracy.":[82]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}