{"id":"https://openalex.org/W2651834199","doi":"https://doi.org/10.1109/icassp.2017.7953215","title":"Non-parallel voice conversion using i-vector PLDA: towards unifying speaker verification and transformation","display_name":"Non-parallel voice conversion using i-vector PLDA: towards unifying speaker verification and transformation","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2651834199","doi":"https://doi.org/10.1109/icassp.2017.7953215","mag":"2651834199"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/62c4ffa6-3985-4c70-b2f3-a3b9ce651861","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["University of Eastern Finland, School of Computing, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Eastern Finland, School of Computing, Finland","institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081575688","display_name":"Lauri Juvela","orcid":"https://orcid.org/0000-0002-2201-103X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lauri Juvela","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","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"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Japan","University of Edinburgh, Centre for Speech Technology-Research, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"University of Edinburgh, Centre for Speech Technology-Research, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.6134,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.98016154,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5535","last_page":"5539"},"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":0.9980000257492065,"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":0.9922999739646912,"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":0.8256233930587769},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7913033962249756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7557850480079651},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5128207802772522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4692178964614868},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43744373321533203},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4351111948490143},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4328475296497345},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4217320680618286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3825869560241699},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3522353172302246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09628862142562866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256233930587769},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7913033962249756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7557850480079651},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5128207802772522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4692178964614868},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43744373321533203},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4351111948490143},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4328475296497345},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4217320680618286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3825869560241699},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3522353172302246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09628862142562866},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2017.7953215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/62c4ffa6-3985-4c70-b2f3-a3b9ce651861","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/62c4ffa6-3985-4c70-b2f3-a3b9ce651861","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kinnunen, T, Juvela, L, Alku, P & Yamagishi, J 2017, Non-Parallel Voice Conversion Using I-Vector PLDA: Towards Unifying Speaker Verification and Transformation. in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 5535-5539, 42nd IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, Louisiana, United States, 5/03/17. https://doi.org/10.1109/ICASSP.2017.7953215","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/62c4ffa6-3985-4c70-b2f3-a3b9ce651861","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/62c4ffa6-3985-4c70-b2f3-a3b9ce651861","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/62c4ffa6-3985-4c70-b2f3-a3b9ce651861","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/62c4ffa6-3985-4c70-b2f3-a3b9ce651861","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kinnunen, T, Juvela, L, Alku, P & Yamagishi, J 2017, Non-Parallel Voice Conversion Using I-Vector PLDA: Towards Unifying Speaker Verification and Transformation. in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 5535-5539, 42nd IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, Louisiana, United States, 5/03/17. https://doi.org/10.1109/ICASSP.2017.7953215","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W142801778","https://openalex.org/W204053250","https://openalex.org/W577640895","https://openalex.org/W1588266896","https://openalex.org/W1966264494","https://openalex.org/W1969728648","https://openalex.org/W1995552268","https://openalex.org/W2041823554","https://openalex.org/W2100649345","https://openalex.org/W2121812409","https://openalex.org/W2121848673","https://openalex.org/W2123808477","https://openalex.org/W2143597468","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2153057929","https://openalex.org/W2154278880","https://openalex.org/W2156142001","https://openalex.org/W2258411824","https://openalex.org/W2294814385","https://openalex.org/W2404874347","https://openalex.org/W2406312423","https://openalex.org/W2475998840","https://openalex.org/W2605320104","https://openalex.org/W2619183452","https://openalex.org/W4235154690","https://openalex.org/W6608353291","https://openalex.org/W6616746457","https://openalex.org/W6713414053","https://openalex.org/W6713727690","https://openalex.org/W6736204136"],"related_works":["https://openalex.org/W2747262669","https://openalex.org/W58284675","https://openalex.org/W1901037250","https://openalex.org/W1946464671","https://openalex.org/W2066941761","https://openalex.org/W2143803185","https://openalex.org/W2018305822","https://openalex.org/W2687193347","https://openalex.org/W2096510939","https://openalex.org/W4283395349"],"abstract_inverted_index":{"Text-independent":[0],"speaker":[1],"verification":[2],"(recognizing":[3],"speakers":[4],"regardless":[5],"of":[6,36,60,68],"content)":[7],"and":[8,57],"non-parallel":[9],"voice":[10,13,28,43,78],"conversion":[11,44],"(transforming":[12],"identities":[14],"without":[15],"requiring":[16],"content-matched":[17],"training":[18,61],"utterances)":[19],"are":[20],"related":[21],"problems.":[22],"We":[23,70],"adopt":[24,71],"i-vector":[25,31],"method":[26],"to":[27,50],"conversion.":[29,79],"An":[30],"is":[32],"a":[33,37],"fixed-dimensional":[34],"representation":[35],"speech":[38],"utterance":[39,46],"that":[40],"enables":[41],"treating":[42],"in":[45],"domain,":[47],"as":[48],"opposed":[49],"frame":[51],"domain.":[52],"The":[53,80],"high":[54],"dimensionality":[55],"(800)":[56],"small":[58],"number":[59],"utterances":[62],"(24)":[63],"necessitates":[64],"using":[65],"prior":[66],"information":[67],"speakers.":[69],"probabilistic":[72],"linear":[73],"discriminant":[74],"analysis":[75],"(PLDA)":[76],"for":[77],"proposed":[81],"approach":[82],"requires":[83],"neither":[84],"parallel":[85],"utterances,":[86],"transcriptions":[87],"nor":[88],"time":[89],"alignment":[90],"procedures":[91],"at":[92],"any":[93],"stage.":[94]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}