{"id":"https://openalex.org/W2407281753","doi":"https://doi.org/10.1109/icassp.2016.7472758","title":"The matching-minimization algorithm, the INCA algorithm and a mathematical framework for voice conversion with unaligned corpora","display_name":"The matching-minimization algorithm, the INCA algorithm and a mathematical framework for voice conversion with unaligned corpora","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2407281753","doi":"https://doi.org/10.1109/icassp.2016.7472758","mag":"2407281753"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5024140675","display_name":"Yannis Agiomyrgiannakis","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yannis Agiomyrgiannakis","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024140675"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":5.1417,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.95690479,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"5645","last_page":"5649"},"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":0.9994000196456909,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/algorithm","display_name":"Algorithm","score":0.8003692626953125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.757473886013031},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6824245452880859},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6797822713851929},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.6429029107093811},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6355036497116089},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6148489117622375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3600984811782837},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13580292463302612}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.8003692626953125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757473886013031},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6824245452880859},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6797822713851929},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.6429029107093811},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6355036497116089},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6148489117622375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3600984811782837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13580292463302612},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W59075858","https://openalex.org/W344150399","https://openalex.org/W1492383498","https://openalex.org/W1520370180","https://openalex.org/W1563460361","https://openalex.org/W1583154192","https://openalex.org/W1600722501","https://openalex.org/W1861150963","https://openalex.org/W1882624840","https://openalex.org/W1963778986","https://openalex.org/W2032130465","https://openalex.org/W2102003408","https://openalex.org/W2110584444","https://openalex.org/W2114551781","https://openalex.org/W2121981798","https://openalex.org/W2123003832","https://openalex.org/W2149115660","https://openalex.org/W2156142001","https://openalex.org/W2161476805","https://openalex.org/W2161877964","https://openalex.org/W2174383933","https://openalex.org/W2294351487","https://openalex.org/W2317898072","https://openalex.org/W2404109308","https://openalex.org/W6685408373"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W4301594054","https://openalex.org/W2794488505","https://openalex.org/W1517908938","https://openalex.org/W2396122647","https://openalex.org/W3125889879","https://openalex.org/W2136161268","https://openalex.org/W3124422538","https://openalex.org/W2295467472","https://openalex.org/W3046451053"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,22,29,35,41,53,63,72,121,160],"mathematical":[4],"framework":[5],"that":[6,43,61],"is":[7,19,48,62,87,103,156],"suitable":[8,157],"for":[9,24,98,116],"voice":[10],"conversion":[11,18],"and":[12,34,71,93,131,137],"adaptation":[13,162],"in":[14,68,76,142],"speech":[15],"processing.":[16],"Voice":[17],"formulated":[20],"as":[21,84],"search":[23],"the":[25,77,107,111,124],"optimal":[26,95],"correspondances":[27],"between":[28,56,129],"set":[30,36],"of":[31,37,59,110],"source-speaker":[32],"spectra":[33,39],"target-speaker":[38],"under":[40],"transform":[42],"compensates":[44],"speaker":[45],"differences.":[46],"It":[47],"possible":[49],"to":[50,83,106],"simultaneously":[51],"recover":[52],"bi-directional":[54],"mapping":[55,65,74],"two":[57],"sets":[58],"vectors":[60],"parametric":[64],"(a":[66],"transform)":[67],"one":[69],"direction":[70],"non-parametric":[73],"(correspondences)":[75],"reverse":[78],"direction.":[79],"An":[80],"algorithm":[81,102,114],"referred":[82],"Matching-Minimization":[85],"(MM)":[86],"formally":[88],"derived":[89],"with":[90],"proven":[91],"convergence":[92],"an":[94],"closed-form":[96],"solution":[97],"each":[99],"step.":[100],"The":[101,127],"closely":[104],"related":[105],"asymmetric-1":[108],"variant":[109],"well-known":[112],"INCA":[113,132,141],"[1]":[115],"which":[117],"we":[118],"also":[119],"provide":[120],"proof":[122],"within":[123],"same":[125],"framework.":[126],"differences":[128],"MM":[130,139,147,155],"are":[133,164],"delineated":[134],"both":[135],"theoretically":[136],"experimentally.":[138],"outperforms":[140],"all":[143],"scenarios.":[144],"Like":[145],"INCA,":[146,154],"does":[148],"not":[149],"require":[150],"parallel":[151],"corpora.":[152],"Unlike":[153],"when":[158],"only":[159],"few":[161],"data":[163],"available.":[165]},"counts_by_year":[{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}