{"id":"https://openalex.org/W4413368306","doi":"https://doi.org/10.1007/978-3-032-02548-7_8","title":"An Exploration of\u00a0ECAPA-TDNN and\u00a0x-vector Speaker Representations in\u00a0Zero-Shot Multi-speaker TTS","display_name":"An Exploration of\u00a0ECAPA-TDNN and\u00a0x-vector Speaker Representations in\u00a0Zero-Shot Multi-speaker TTS","publication_year":2025,"publication_date":"2025-08-21","ids":{"openalex":"https://openalex.org/W4413368306","doi":"https://doi.org/10.1007/978-3-032-02548-7_8"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-02548-7_8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-02548-7_8","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.20190","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050568080","display_name":"Marie Kune\u0161ov\u00e1","orcid":"https://orcid.org/0000-0002-7187-8481"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Marie Kune\u0161ov\u00e1","raw_affiliation_strings":["NTIS Research Centre and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia in Pilsen, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-7187-8481","affiliations":[{"raw_affiliation_string":"NTIS Research Centre and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia in Pilsen, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064576255","display_name":"Zden\u011bk Hanzl\u00ed\u010dek","orcid":"https://orcid.org/0000-0002-4001-9289"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Zden\u011bk Hanzl\u00ed\u010dek","raw_affiliation_strings":["NTIS Research Centre and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia in Pilsen, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-4001-9289","affiliations":[{"raw_affiliation_string":"NTIS Research Centre and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia in Pilsen, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030642609","display_name":"Jind\u0159ich Matou\u0161ek","orcid":"https://orcid.org/0000-0002-7408-7730"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jind\u0159ich Matou\u0161ek","raw_affiliation_strings":["NTIS Research Centre and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia in Pilsen, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-7408-7730","affiliations":[{"raw_affiliation_string":"NTIS Research Centre and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia in Pilsen, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050568080"],"corresponding_institution_ids":["https://openalex.org/I92715842"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35567959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"95"},"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":0.9970999956130981,"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":0.9908000230789185,"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":0.7899739742279053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6711267232894897},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5909212231636047},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5230035185813904},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.46327778697013855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45120182633399963},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44005727767944336},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4170985221862793},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41174179315567017},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0785185694694519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899739742279053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6711267232894897},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5909212231636047},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5230035185813904},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.46327778697013855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45120182633399963},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44005727767944336},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4170985221862793},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41174179315567017},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0785185694694519},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-032-02548-7_8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-02548-7_8","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2506.20190","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.20190","pdf_url":"https://arxiv.org/pdf/2506.20190","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"pmh:oai:arXiv.org:2506.20190","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.20190","pdf_url":"https://arxiv.org/pdf/2506.20190","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2150769028","https://openalex.org/W2612434969","https://openalex.org/W2726515241","https://openalex.org/W2746498480","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2962788625","https://openalex.org/W2963371159","https://openalex.org/W2974231335","https://openalex.org/W3015826515","https://openalex.org/W3024869864","https://openalex.org/W3090254849","https://openalex.org/W3143367551","https://openalex.org/W3167533889","https://openalex.org/W3197186969","https://openalex.org/W3197580070","https://openalex.org/W3205878676","https://openalex.org/W3209984917","https://openalex.org/W4319586596","https://openalex.org/W4392904093","https://openalex.org/W4402111360","https://openalex.org/W4402112243","https://openalex.org/W4408353942"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4389984014","https://openalex.org/W1940231550","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
