{"id":"https://openalex.org/W3184815887","doi":"https://doi.org/10.1109/lsp.2022.3152672","title":"SVSNet: An End-to-End Speaker Voice Similarity Assessment Model","display_name":"SVSNet: An End-to-End Speaker Voice Similarity Assessment Model","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3184815887","doi":"https://doi.org/10.1109/lsp.2022.3152672","mag":"3184815887"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2022.3152672","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3152672","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/9686799/09716822.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/97/9686799/09716822.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090637127","display_name":"Cheng-Hung Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Hung Hu","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-6112-9380","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066130866","display_name":"Yuhuai Peng","orcid":"https://orcid.org/0000-0001-9343-5377"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Huai Peng","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Chiyoda-ku, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2752-3955","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Chiyoda-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-6956-0418","affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-3599-5071","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9711,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78743464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"29","issue":null,"first_page":"767","last_page":"771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9968000054359436,"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":0.7995997667312622},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6880528330802917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6876147985458374},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6213513016700745},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.596172571182251},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5604960322380066},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4666307866573334},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4551912844181061},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4426320195198059},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43103867769241333},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4254502058029175},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4122142493724823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40389537811279297},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3967563807964325},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08298161625862122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995997667312622},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6880528330802917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6876147985458374},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6213513016700745},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.596172571182251},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5604960322380066},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4666307866573334},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4551912844181061},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4426320195198059},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43103867769241333},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4254502058029175},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4122142493724823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40389537811279297},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3967563807964325},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08298161625862122},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2022.3152672","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3152672","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/9686799/09716822.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2107.09392","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.09392","pdf_url":"https://arxiv.org/pdf/2107.09392","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"doi:10.1109/lsp.2022.3152672","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3152672","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/9686799/09716822.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3184815887.pdf","grobid_xml":"https://content.openalex.org/works/W3184815887.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1546892833","https://openalex.org/W1552314771","https://openalex.org/W1966192511","https://openalex.org/W1998648683","https://openalex.org/W2003788511","https://openalex.org/W2046056978","https://openalex.org/W2067295501","https://openalex.org/W2075843680","https://openalex.org/W2078483536","https://openalex.org/W2107860279","https://openalex.org/W2113131123","https://openalex.org/W2144404214","https://openalex.org/W2151967815","https://openalex.org/W2277581165","https://openalex.org/W2401447047","https://openalex.org/W2423557781","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2746321128","https://openalex.org/W2794506738","https://openalex.org/W2802488037","https://openalex.org/W2805215415","https://openalex.org/W2890964092","https://openalex.org/W2903739847","https://openalex.org/W2937033898","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2962896155","https://openalex.org/W2963035245","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2963403924","https://openalex.org/W2963636093","https://openalex.org/W2964052309","https://openalex.org/W2964227577","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972394484","https://openalex.org/W2972909277","https://openalex.org/W2973196014","https://openalex.org/W3008880747","https://openalex.org/W3009032512","https://openalex.org/W3015338123","https://openalex.org/W3015579786","https://openalex.org/W3082130377","https://openalex.org/W3083776549","https://openalex.org/W3097206152","https://openalex.org/W3099330747","https://openalex.org/W3131643166","https://openalex.org/W3132528633","https://openalex.org/W3152426975","https://openalex.org/W3161480375","https://openalex.org/W3161558238","https://openalex.org/W3185109982","https://openalex.org/W6739901393","https://openalex.org/W6752308553","https://openalex.org/W6767111847","https://openalex.org/W6785764544","https://openalex.org/W6785906987"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W2806010980","https://openalex.org/W4235705411","https://openalex.org/W2972909277","https://openalex.org/W4380906377","https://openalex.org/W2587150483","https://openalex.org/W204267554","https://openalex.org/W2972441390","https://openalex.org/W3108238911"],"abstract_inverted_index":{"Neural":[0],"evaluation":[1,45],"metrics":[2,46],"derived":[3],"for":[4,38,65],"numerous":[5],"speech":[6,34,37,63],"generation":[7],"tasks":[8],"have":[9],"recently":[10],"attracted":[11],"great":[12],"attention.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17],"propose":[18],"SVSNet,":[19],"the":[20,28,54,88,107,113],"first":[21],"end-to-end":[22,82],"neural":[23,44],"network":[24],"model":[25],"to":[26,59],"assess":[27],"speaker":[29,110],"voice":[30,39],"similarity":[31,111],"between":[32],"converted":[33],"and":[35,74,77,93,96,115],"natural":[36],"conversion":[40],"tasks.":[41],"Unlike":[42],"most":[43],"that":[47,100],"use":[48],"hand-crafted":[49],"features,":[50],"SVSNet":[51,67,101],"directly":[52],"takes":[53],"raw":[55],"waveform":[56],"as":[57],"input":[58],"more":[60],"completely":[61],"utilize":[62],"information":[64],"prediction.":[66],"consists":[68],"of":[69,109],"encoder,":[70],"co-attention,":[71],"distance":[72],"calculation,":[73],"prediction":[75],"modules":[76],"is":[78],"trained":[79],"in":[80,106],"an":[81],"manner.":[83],"The":[84],"experimental":[85],"results":[86],"on":[87],"Voice":[89],"Conversion":[90],"Challenge":[91],"2018":[92],"2020":[94],"(VCC2018":[95],"VCC2020)":[97],"datasets":[98],"show":[99],"outperforms":[102],"well-known":[103],"baseline":[104],"systems":[105],"assessment":[108],"at":[112],"utterance":[114],"system":[116],"levels.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}