{"id":"https://openalex.org/W2747210965","doi":"https://doi.org/10.1109/taslp.2017.2743620","title":"Spectral Mapping Using Prior Re-Estimation of i-Vectors and System Fusion for Voice Conversion","display_name":"Spectral Mapping Using Prior Re-Estimation of i-Vectors and System Fusion for Voice Conversion","publication_year":2017,"publication_date":"2017-08-23","ids":{"openalex":"https://openalex.org/W2747210965","doi":"https://doi.org/10.1109/taslp.2017.2743620","mag":"2747210965"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2743620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2743620","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101586349","display_name":"Monisankha Pal","orcid":"https://orcid.org/0000-0002-8234-0222"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Monisankha Pal","raw_affiliation_strings":["Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology, Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology, Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069790572","display_name":"Goutam Saha","orcid":"https://orcid.org/0000-0001-6187-1684"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Goutam Saha","raw_affiliation_strings":["Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology, Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology, Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101586349"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":0.39,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70350399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"25","issue":"11","first_page":"2071","last_page":"2084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9771999716758728,"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/fusion","display_name":"Fusion","score":0.6057120561599731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5119968056678772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4659467935562134},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4393223524093628},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36115726828575134},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1348462998867035},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09265610575675964},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05778658390045166}],"concepts":[{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6057120561599731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5119968056678772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4659467935562134},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4393223524093628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36115726828575134},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1348462998867035},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09265610575675964},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05778658390045166},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2743620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2743620","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W33533989","https://openalex.org/W1484305213","https://openalex.org/W1508196967","https://openalex.org/W1523372075","https://openalex.org/W1963778986","https://openalex.org/W1964420823","https://openalex.org/W1968689546","https://openalex.org/W1969728648","https://openalex.org/W1975341057","https://openalex.org/W1977362459","https://openalex.org/W1999651846","https://openalex.org/W2005438552","https://openalex.org/W2007023536","https://openalex.org/W2045036776","https://openalex.org/W2049686551","https://openalex.org/W2067234399","https://openalex.org/W2077740952","https://openalex.org/W2086796102","https://openalex.org/W2091456738","https://openalex.org/W2097998348","https://openalex.org/W2105698384","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2121415728","https://openalex.org/W2123003832","https://openalex.org/W2123299109","https://openalex.org/W2125027820","https://openalex.org/W2144404214","https://openalex.org/W2145130307","https://openalex.org/W2146448989","https://openalex.org/W2150769028","https://openalex.org/W2151262064","https://openalex.org/W2153057929","https://openalex.org/W2156142001","https://openalex.org/W2156477760","https://openalex.org/W2157412983","https://openalex.org/W2161476805","https://openalex.org/W2165674530","https://openalex.org/W2168561756","https://openalex.org/W2230477019","https://openalex.org/W2343023855","https://openalex.org/W2395273272","https://openalex.org/W2485388802","https://openalex.org/W2574092538","https://openalex.org/W2602814339","https://openalex.org/W2651834199","https://openalex.org/W3011402798","https://openalex.org/W6600438624","https://openalex.org/W6601370681","https://openalex.org/W6630462654","https://openalex.org/W6631309588","https://openalex.org/W6674385629","https://openalex.org/W6682053583","https://openalex.org/W6711789357"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"In":[0,174],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,40,67,131],"new":[6],"voice":[7],"conversion":[8,62],"(VC)":[9],"method":[10],"using":[11,39],"i-vectors":[12],"which":[13],"consider":[14],"low-dimensional":[15],"representation":[16],"of":[17,33,47,61,104,110,168],"speech":[18,183],"utterances.":[19],"An":[20],"attempt":[21],"is":[22,90],"made":[23],"to":[24,65,186],"restrict":[25],"the":[26,30,48,54,101,126,176],"i-vector":[27,86],"variability":[28,35],"in":[29,108,151],"intermediate":[31,49],"computation":[32],"total":[34],"(T)":[36],"matrix":[37],"by":[38],"novel":[41],"approach":[42],"that":[43,125],"uses":[44],"modified-prior":[45],"distribution":[46],"i-vectors.":[50],"This":[51],"T-modification":[52],"improves":[53],"speaker":[55],"individuality":[56],"conversion.":[57],"For":[58],"further":[59],"improvement":[60],"score":[63,138],"and":[64,72,85,99,112,136,164],"keep":[66],"better":[68,132,148,161,180],"balance":[69],"between":[70,77,134],"similarity":[71,135],"quality,":[73],"band-wise":[74],"spectrogram":[75,94],"fusion":[76],"conventional":[78],"joint":[79],"density":[80],"Gaussian":[81],"mixture":[82,167],"model":[83],"(JDGMM)":[84],"based":[87,171],"converted":[88,182],"spectrograms":[89],"employed.":[91],"The":[92,122,156],"fused":[93],"retains":[95],"more":[96],"spectral":[97],"details":[98],"leverages":[100],"complementary":[102],"merits":[103],"each":[105],"subsystem.":[106],"Experiments":[107],"terms":[109],"objective":[111,163],"subjective":[113],"evaluation":[114],"are":[115],"conducted":[116],"extensively":[117],"on":[118],"CMU":[119],"ARCTIC":[120],"database.":[121],"results":[123],"show":[124],"proposed":[127,157,177],"technique":[128],"can":[129],"produce":[130],"trade-off":[133],"quality":[137,181],"than":[139,149,166],"other":[140],"state-of-the-art":[141],"baseline":[142,172],"VC":[143,153,158,178,189],"methods.":[144],"Furthermore,":[145],"it":[146],"works":[147],"JDGMM":[150],"limited":[152],"training":[154],"data.":[155],"performs":[159],"moderately":[160],"(both":[162],"subjective)":[165],"factor":[169],"analyzer":[170],"VC.":[173],"addition,":[175],"provides":[179],"as":[184],"compared":[185],"maximum":[187],"likelihood-GMM":[188],"with":[190],"dynamic":[191],"feature":[192],"constraint.":[193]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}