{"id":"https://openalex.org/W4283731195","doi":"https://doi.org/10.21437/interspeech.2022-11305","title":"A Hierarchical Speaker Representation Framework for One-shot Singing Voice Conversion","display_name":"A Hierarchical Speaker Representation Framework for One-shot Singing Voice Conversion","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283731195","doi":"https://doi.org/10.21437/interspeech.2022-11305"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11305","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11305","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5100342434","display_name":"Xu Li","orcid":"https://orcid.org/0000-0002-0345-7677"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Li","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066070154","display_name":"Shansong Liu","orcid":"https://orcid.org/0000-0001-6202-5615"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shansong Liu","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100342434"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.8315,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73491704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4307","last_page":"4311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7732332944869995},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6498562097549438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6028496026992798},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5824309587478638},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.45973408222198486},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13701921701431274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7732332944869995},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6498562097549438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6028496026992798},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5824309587478638},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.45973408222198486},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13701921701431274},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11305","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11305","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2067709094","https://openalex.org/W2502312327","https://openalex.org/W2593414223","https://openalex.org/W2760103357","https://openalex.org/W2921857201","https://openalex.org/W2970006822","https://openalex.org/W2972659941","https://openalex.org/W2972812066","https://openalex.org/W2989708046","https://openalex.org/W3015338123","https://openalex.org/W3016007107","https://openalex.org/W3024869864","https://openalex.org/W3047855478","https://openalex.org/W3095948607","https://openalex.org/W3097152652","https://openalex.org/W3097777922","https://openalex.org/W3110041771","https://openalex.org/W3123097577","https://openalex.org/W3170751106","https://openalex.org/W3181854487","https://openalex.org/W3199364993","https://openalex.org/W3206191467","https://openalex.org/W4221151538","https://openalex.org/W4226320669","https://openalex.org/W4226348722","https://openalex.org/W4287116649","https://openalex.org/W4291923699"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Typically,":[0],"singing":[1,28],"voice":[2],"conversion":[3],"(SVC)":[4],"depends":[5],"on":[6],"an":[7,83],"embedding":[8,42],"vector,":[9],"extracted":[10],"from":[11],"either":[12],"a":[13,19,40,64,165],"speaker":[14,20,26,32,50,67,76,123,139],"lookup":[15],"table":[16],"(LUT)":[17],"or":[18],"recognition":[21],"network":[22],"(SRN),":[23],"to":[24,136],"model":[25],"identity.However,":[27],"contains":[29],"more":[30],"expressive":[31],"characteristics":[33,77,124],"than":[34],"conversational":[35],"speech.It":[36],"is":[37,53,111],"suspected":[38],"that":[39,113,143],"single":[41],"vector":[43],"may":[44],"only":[45,164],"capture":[46,74],"averaged":[47],"and":[48,86,151],"coarse-grained":[49],"characteristics,":[51],"which":[52,72,128],"insufficient":[54],"for":[55,70],"the":[56,93,104,108,114,133,138,144,149,156,160],"SVC":[57,154,162],"task.To":[58],"this":[59,61],"end,":[60],"work":[62],"proposes":[63],"novel":[65],"hierarchical":[66],"representation":[68],"framework":[69],"SVC,":[71],"can":[73,121],"fine-grained":[75],"at":[78,125],"different":[79,126],"granularity.It":[80],"consists":[81],"of":[82,103,117,168],"up-sampling":[84,90,134],"stream":[85,91,102],"three":[87,105],"down-sampling":[88,119],"streams.The":[89],"transforms":[92],"linguistic":[94],"features":[95],"into":[96],"audio":[97],"samples,":[98],"while":[99],"one":[100],"downsampling":[101],"operates":[106],"in":[107,132],"reverse":[109],"direction.It":[110],"expected":[112],"temporal":[115],"statistics":[116],"each":[118],"block":[120],"represent":[122],"granularity,":[127],"will":[129],"be":[130],"engaged":[131],"blocks":[135],"enhance":[137],"modeling.Experiment":[140],"results":[141],"verify":[142],"proposed":[145,157],"method":[146],"outperforms":[147],"both":[148],"LUT":[150],"SRN":[152],"based":[153],"systems.Moreover,":[155],"system":[158],"supports":[159],"one-shot":[161],"with":[163],"few":[166],"seconds":[167],"reference":[169],"audio.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}