{"id":"https://openalex.org/W2032130465","doi":"https://doi.org/10.1109/icassp.2014.6855140","title":"Non-parallel voice conversion using joint optimization of alignment by temporal context and spectral distortion","display_name":"Non-parallel voice conversion using joint optimization of alignment by temporal context and spectral distortion","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2032130465","doi":"https://doi.org/10.1109/icassp.2014.6855140","mag":"2032130465"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6855140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5029174249","display_name":"Hadas Benisty","orcid":"https://orcid.org/0000-0001-6308-2267"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"H. Benisty","raw_affiliation_strings":["Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, Israel","Dept. of Electr.Eng., Technion-Israel Inst. of Technol., Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Dept. of Electr.Eng., Technion-Israel Inst. of Technol., Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009813683","display_name":"D. Malah","orcid":"https://orcid.org/0009-0001-8310-7844"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"D. Malah","raw_affiliation_strings":["Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, Israel","Dept. of Electr.Eng., Technion-Israel Inst. of Technol., Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Dept. of Electr.Eng., Technion-Israel Inst. of Technol., Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006419939","display_name":"Koby Crammer","orcid":"https://orcid.org/0000-0001-8824-5747"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"K. Crammer","raw_affiliation_strings":["Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, Israel","Dept. of Electr.Eng., Technion-Israel Inst. of Technol., Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Dept. of Electr.Eng., Technion-Israel Inst. of Technol., Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029174249"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":3.2721,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92811143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"7909","last_page":"7913"},"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":0.9994999766349792,"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":0.8375083804130554},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7206695675849915},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6679178476333618},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6524840593338013},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6339687705039978},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6121932864189148},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.5038489699363708},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4746031165122986},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4484559893608093},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.446845680475235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.436532199382782},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43638795614242554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38327494263648987},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11701947450637817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8375083804130554},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7206695675849915},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6679178476333618},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6524840593338013},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6339687705039978},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6121932864189148},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5038489699363708},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4746031165122986},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4484559893608093},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.446845680475235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.436532199382782},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43638795614242554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38327494263648987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11701947450637817},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6855140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W142801778","https://openalex.org/W167578630","https://openalex.org/W1526513105","https://openalex.org/W1588266896","https://openalex.org/W2067175291","https://openalex.org/W2105160541","https://openalex.org/W2110584444","https://openalex.org/W2117154045","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2123003832","https://openalex.org/W2129082420","https://openalex.org/W2136166660","https://openalex.org/W2156142001","https://openalex.org/W2161476805","https://openalex.org/W2169579015","https://openalex.org/W3177989406","https://openalex.org/W3193262203","https://openalex.org/W6635216677","https://openalex.org/W6684957941","https://openalex.org/W6799352683"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W1972035260","https://openalex.org/W2888483922","https://openalex.org/W2367747139","https://openalex.org/W2794488505","https://openalex.org/W4391102217","https://openalex.org/W4301594054","https://openalex.org/W1517908938","https://openalex.org/W2328889547"],"abstract_inverted_index":{"Many":[0],"voice":[1],"conversion":[2,29,48,102],"systems":[3],"require":[4],"parallel":[5],"training":[6,15,87,146],"sets":[7,147],"of":[8,23,45,93,139],"the":[9,28,86,109,123,140],"source":[10],"and":[11,47,101,112],"target":[12],"speakers.":[13],"Non-parallel":[14],"is":[16,33,52],"more":[17],"complicated":[18],"as":[19,74,89],"it":[20],"involves":[21],"evaluation":[22],"source-target":[24,65],"correspondence":[25],"along":[26],"with":[27],"function":[30],"itself.":[31],"INCA":[32,76],"a":[34,55,70,90,94],"recently":[35],"proposed":[36],"method":[37],"for":[38],"non-parallel":[39],"training,":[40],"based":[41,78],"on":[42,79],"iterative":[43],"estimation":[44],"alignment":[46,51,100,124],"function.":[49,103],"The":[50],"evaluated":[53],"using":[54],"simple":[56],"nearest-neighbor":[57],"search,":[58],"which":[59],"often":[60],"leads":[61,135],"to":[62,127,136],"phonetic":[63],"miss-matched":[64],"pairs.":[66],"We":[67,84,104],"propose":[68],"here":[69],"generalized":[71],"approach,":[72],"denoted":[73],"Temporal-Context":[75],"(TC-INCA),":[77],"matching":[80],"temporal":[81],"context":[82],"vectors.":[83],"formulate":[85],"stage":[88],"minimization":[91],"problem":[92],"joint":[95,110],"cost,":[96],"considering":[97],"both":[98],"context-based":[99],"show":[105,132],"that":[106,119,133],"TC-INCA":[107,120,134],"reduces":[108],"cost":[111],"prove":[113],"its":[114],"convergence.":[115],"Experimental":[116],"results":[117],"indicate":[118],"significantly":[121],"improves":[122],"accuracy,":[125],"compared":[126],"INCA.":[128],"Moreover,":[129],"subjective":[130],"evaluations":[131],"improved":[137],"quality":[138],"synthesized":[141],"output":[142],"signals,":[143],"when":[144],"small":[145],"are":[148],"used.":[149]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
