{"id":"https://openalex.org/W1969728648","doi":"https://doi.org/10.1109/lsp.2012.2225615","title":"Mixture of Factor Analyzers Using Priors From Non-Parallel Speech for Voice Conversion","display_name":"Mixture of Factor Analyzers Using Priors From Non-Parallel Speech for Voice Conversion","publication_year":2012,"publication_date":"2012-10-19","ids":{"openalex":"https://openalex.org/W1969728648","doi":"https://doi.org/10.1109/lsp.2012.2225615","mag":"1969728648"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2012.2225615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2012.2225615","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/208cab6d-2200-4f30-bad9-09949e6397c2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":["School of Computer Engineering, Temasek Lab@NTU, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Temasek Lab@NTU, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","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"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Joensuu, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Engineering, Temasek Lab@NTU, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Temasek Lab@NTU, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","School of Computer Engineering, Nanyang Technological University, Singapore","University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6666,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.9278991,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"12","first_page":"914","last_page":"917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.998199999332428,"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":0.9764999747276306,"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":0.7982223033905029},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6724942922592163},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.5940686464309692},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5098813772201538},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4835355281829834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46151137351989746},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4436948299407959},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4309467673301697},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.11068525910377502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982223033905029},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6724942922592163},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.5940686464309692},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5098813772201538},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4835355281829834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46151137351989746},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4436948299407959},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4309467673301697},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.11068525910377502},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/lsp.2012.2225615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2012.2225615","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/208cab6d-2200-4f30-bad9-09949e6397c2","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/208cab6d-2200-4f30-bad9-09949e6397c2","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Wu, Z, Kinnunen, T, Chng, E S & Li, H 2012, 'Mixture of Factor Analyzers Using Priors from Non-Parallel Speech for Voice Conversion', IEEE Signal Processing Letters, vol. 19, no. 12, pp. 914-917. https://doi.org/10.1109/LSP.2012.2225615","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.304.6118","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.304.6118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.joensuu.fi/pages/tkinnu/webpage/pdf/TMFA_IEEESPL_2012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.706.4406","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.706.4406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.uef.fi/sipu/pub/Wu_IEEESPL_factor_analysis.pdf","raw_type":"text"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/102726","is_oa":false,"landing_page_url":"http://hdl.handle.net/10220/16436","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/208cab6d-2200-4f30-bad9-09949e6397c2","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/208cab6d-2200-4f30-bad9-09949e6397c2","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/208cab6d-2200-4f30-bad9-09949e6397c2","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/208cab6d-2200-4f30-bad9-09949e6397c2","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Wu, Z, Kinnunen, T, Chng, E S & Li, H 2012, 'Mixture of Factor Analyzers Using Priors from Non-Parallel Speech for Voice Conversion', IEEE Signal Processing Letters, vol. 19, no. 12, pp. 914-917. https://doi.org/10.1109/LSP.2012.2225615","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W1508196967","https://openalex.org/W1662191912","https://openalex.org/W2007023536","https://openalex.org/W2049686551","https://openalex.org/W2105160541","https://openalex.org/W2114543868","https://openalex.org/W2117154045","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2121415728","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2150769028","https://openalex.org/W2156142001","https://openalex.org/W2165108269","https://openalex.org/W6630462654"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W2085259108","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W3123087812","https://openalex.org/W1516392727"],"abstract_inverted_index":{"A":[0],"robust":[1],"voice":[2,30],"conversion":[3,52],"function":[4],"relies":[5],"on":[6,56],"a":[7,35],"large":[8],"amount":[9],"of":[10,37,51,70],"parallel":[11,25],"training":[12,26,50],"data,":[13],"which":[14,41],"is":[15],"difficult":[16],"to":[17],"collect":[18],"in":[19,29],"practice.":[20],"To":[21],"tackle":[22],"the":[23,49,62,66,81,85],"sparse":[24],"data":[27],"problem":[28],"conversion,":[31],"this":[32],"paper":[33],"describes":[34],"mixture":[36],"factor":[38],"analyzers":[39],"method":[40,64,83],"integrates":[42],"prior":[43],"knowledge":[44],"from":[45],"non-parallel":[46],"speech":[47],"into":[48],"function.":[53],"The":[54],"experiments":[55],"CMU":[57],"ARCTIC":[58],"corpus":[59],"show":[60,80],"that":[61],"proposed":[63,82],"improves":[65],"quality":[67],"and":[68,76],"similarity":[69],"converted":[71],"speech.":[72],"With":[73],"both":[74],"objective":[75],"subjective":[77],"evaluations,":[78],"we":[79],"outperforms":[84],"baseline":[86],"GMM":[87],"method.":[88]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}