{"id":"https://openalex.org/W4319586596","doi":"https://doi.org/10.1109/iscslp57327.2022.10037956","title":"ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis","display_name":"ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586596","doi":"https://doi.org/10.1109/iscslp57327.2022.10037956"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037956","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5033565985","display_name":"Jinlong Xue","orcid":"https://orcid.org/0009-0000-0442-0932"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Xue","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008597430","display_name":"Yayue Deng","orcid":"https://orcid.org/0009-0003-7642-4942"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yayue Deng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","Beijing Language and Culture University, Beijing, China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031705836","display_name":"Yichen Han","orcid":"https://orcid.org/0009-0008-7018-8949"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Han","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343662","display_name":"Ya Li","orcid":"https://orcid.org/0000-0002-6284-5039"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047888605","display_name":"Jianqing Sun","orcid":"https://orcid.org/0009-0007-3598-8564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianqing Sun","raw_affiliation_strings":["Unisound AI Technology Co., Ltd,Beijing,China","Unisound AI Technology Co., Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110832899","display_name":"Jiaen Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaen Liang","raw_affiliation_strings":["Unisound AI Technology Co., Ltd,Beijing,China","Unisound AI Technology Co., Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3496,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.83381924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"230","last_page":"234"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9947999715805054,"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":0.8410122990608215},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7612647414207458},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6146632432937622},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6135429739952087},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6069419384002686},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.583725094795227},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.576573371887207},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5292693376541138},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5136300921440125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45580342411994934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410122990608215},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7612647414207458},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6146632432937622},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6135429739952087},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6069419384002686},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.583725094795227},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.576573371887207},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5292693376541138},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5136300921440125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45580342411994934},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037956","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"},{"id":"https://openalex.org/F4320326873","display_name":"National Laboratory of Pattern Recognition","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2473388484","https://openalex.org/W2612434969","https://openalex.org/W2726515241","https://openalex.org/W2747874407","https://openalex.org/W2752782242","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2889093877","https://openalex.org/W2890964092","https://openalex.org/W2963035245","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972394484","https://openalex.org/W3015537910","https://openalex.org/W3015826515","https://openalex.org/W3024869864","https://openalex.org/W3033411150","https://openalex.org/W3093573519","https://openalex.org/W3143367551","https://openalex.org/W3161558238","https://openalex.org/W3161704465","https://openalex.org/W3198270377","https://openalex.org/W6737575990","https://openalex.org/W6752888775","https://openalex.org/W6778823374","https://openalex.org/W6784200033"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"In":[0,32],"recent":[1],"years,":[2],"neural":[3],"network":[4],"based":[5,70,85,124],"methods":[6,25,128,135],"for":[7,52],"multispeaker":[8],"text-to-speech":[9],"synthesis":[10],"(TTS)":[11],"have":[12],"made":[13],"significant":[14],"progress.":[15],"However,":[16],"the":[17,72,115],"current":[18],"speaker":[19,30,39,68,80,95,105],"encoder":[20,40,69,96],"models":[21,97],"used":[22],"in":[23,139],"these":[24,134],"still":[26],"cannot":[27],"capture":[28],"enough":[29],"information.":[31],"this":[33],"paper,":[34],"we":[35,113],"focus":[36],"on":[37,71],"accurate":[38],"modeling":[41],"and":[42,55,87,119,133],"propose":[43],"an":[44],"end-to-end":[45],"method":[46,101],"that":[47],"can":[48,102],"generate":[49],"better":[50,104],"similarity":[51],"both":[53],"seen":[54],"unseen":[56],"speakers.":[57],"The":[58,91],"proposed":[59,100],"architecture":[60],"consists":[61],"of":[62],"three":[63],"separately":[64],"trained":[65],"components:":[66],"a":[67,83,88],"state-of-the-art":[73],"ECAPA-TDNN":[74],"model":[75],"which":[76],"is":[77],"derived":[78],"from":[79],"verification":[81],"task,":[82],"FastSpeech2":[84],"synthesizer,":[86],"HiFi-GAN":[89],"vocoder.":[90],"comparison":[92],"among":[93],"different":[94,121],"shows":[98],"our":[99,110,131],"achieve":[103],"similarity.":[106],"To":[107],"efficiently":[108],"evaluate":[109,120],"synthesized":[111],"speech,":[112],"are":[114],"first":[116],"to":[117,129],"adopt":[118],"deep":[122],"learning":[123],"automatic":[125,140],"MOS":[126],"evaluation":[127],"assess":[130],"results,":[132],"show":[136],"great":[137],"potential":[138],"speech":[141],"quality":[142],"assessment.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}