{"id":"https://openalex.org/W3172021299","doi":"https://doi.org/10.23919/eusipco54536.2021.9616305","title":"Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis","display_name":"Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3172021299","doi":"https://doi.org/10.23919/eusipco54536.2021.9616305","mag":"3172021299"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616305","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616305","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5016558880","display_name":"Be\u00e1ta L\u0151rincz","orcid":"https://orcid.org/0000-0002-7728-5863"},"institutions":[{"id":"https://openalex.org/I3125347698","display_name":"Babe\u0219-Bolyai University","ror":"https://ror.org/02rmd1t30","country_code":"RO","type":"education","lineage":["https://openalex.org/I3125347698"]},{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Beata Lorincz","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca, Romania","Computer Science Department, Babes-Bolyai University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Computer Science Department, Babes-Bolyai University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I3125347698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038722127","display_name":"Mircea Giurgiu","orcid":"https://orcid.org/0009-0007-9789-6083"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Mircea Giurgiu","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016558880"],"corresponding_institution_ids":["https://openalex.org/I158333966","https://openalex.org/I3125347698"],"apc_list":null,"apc_paid":null,"fwci":0.5026,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64572817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"30"},"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":0.9973999857902527,"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":0.9951000213623047,"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":0.8004990816116333},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7703893780708313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7175703644752502},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.692511796951294},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6267472505569458},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5261154770851135},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.46107104420661926},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.454077810049057},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.43821412324905396},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43526989221572876},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4229896366596222},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3714343011379242}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004990816116333},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7703893780708313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7175703644752502},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.692511796951294},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6267472505569458},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5261154770851135},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.46107104420661926},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.454077810049057},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.43821412324905396},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43526989221572876},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4229896366596222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3714343011379242},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616305","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616305","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G5360744958","display_name":null,"funder_award_id":"PN-III-P1-1.2-PCCDI-2017-0818/73","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"}],"funders":[{"id":"https://openalex.org/F4320323983","display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii","ror":"https://ror.org/01q7jq182"},{"id":"https://openalex.org/F4320329037","display_name":"Ministerul Cercet\u0103rii \u015fi Inov\u0103rii","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2120847449","https://openalex.org/W2187089797","https://openalex.org/W2428180336","https://openalex.org/W2591927543","https://openalex.org/W2619368999","https://openalex.org/W2738884019","https://openalex.org/W2766812927","https://openalex.org/W2767052532","https://openalex.org/W2794490148","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2960427821","https://openalex.org/W2963432880","https://openalex.org/W2963609956","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2990124956","https://openalex.org/W2991356003","https://openalex.org/W2997430147","https://openalex.org/W3013020904","https://openalex.org/W3015826515","https://openalex.org/W3015853838","https://openalex.org/W3025528898","https://openalex.org/W3033194228","https://openalex.org/W3095545636","https://openalex.org/W3096086473","https://openalex.org/W3097290232","https://openalex.org/W3097448764","https://openalex.org/W3161492781","https://openalex.org/W6734815144","https://openalex.org/W6745697700","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6753855596","https://openalex.org/W6763832098","https://openalex.org/W6765653190","https://openalex.org/W6765987481","https://openalex.org/W6770838157","https://openalex.org/W6772357204","https://openalex.org/W6777567901","https://openalex.org/W6778083308","https://openalex.org/W6785653481"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4391272374","https://openalex.org/W4400309480","https://openalex.org/W2549308614","https://openalex.org/W2081919107"],"abstract_inverted_index":{"Building":[0],"multispeaker":[1,55,142],"neural":[2],"network-based":[3],"text-to-speech":[4],"synthesis":[5],"systems":[6],"commonly":[7],"relies":[8],"on":[9,27,32],"the":[10,24,28,48,54,82,99,130,134,138,141],"availability":[11],"of":[12,15,36,50,140],"large":[13],"amounts":[14],"high":[16],"quality":[17],"recordings":[18],"from":[19,44],"each":[20,45,104],"speaker":[21,67,88,105,131],"and":[22,62,69,97,122],"conditioning":[23],"training":[25],"process":[26],"speaker's":[29],"identity":[30,89],"or":[31,47],"a":[33,86],"learned":[34],"representation":[35,90],"it.":[37],"However,":[38],"when":[39,117],"little":[40],"data":[41,101,135],"is":[42,52],"available":[43],"speaker,":[46],"number":[49],"speakers":[51],"limited,":[53],"TTS":[56,143],"can":[57],"be":[58],"hard":[59],"to":[60,73,84,103],"train":[61],"will":[63],"result":[64],"in":[65],"poor":[66],"similarity":[68],"naturalness.":[70],"In":[71],"order":[72],"address":[74],"this":[75],"issue,":[76],"we":[77],"explore":[78],"two":[79],"directions:":[80],"forcing":[81],"network":[83],"learn":[85],"better":[87],"by":[91],"appending":[92],"an":[93],"additional":[94,126],"loss":[95,127],"term;":[96],"augmenting":[98],"input":[100],"pertaining":[102],"using":[106],"waveform":[107],"manipulation":[108],"methods.":[109],"We":[110],"show":[111],"that":[112],"both":[113,120],"methods":[114],"are":[115],"efficient":[116],"evaluated":[118],"with":[119],"objective":[121],"subjective":[123],"measures.":[124],"The":[125],"term":[128],"aids":[129],"similarity,":[132],"while":[133],"augmentation":[136],"improves":[137],"Intelligibility":[139],"system.":[144]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
