{"id":"https://openalex.org/W2921343178","doi":"https://doi.org/10.23919/apsipa.2018.8659638","title":"Novel Inter Mixture Weighted GMM Posteriorgram for DNN and GAN-based Voice Conversion","display_name":"Novel Inter Mixture Weighted GMM Posteriorgram for DNN and GAN-based Voice Conversion","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921343178","doi":"https://doi.org/10.23919/apsipa.2018.8659638","mag":"2921343178"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659638","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5091143209","display_name":"Nirmesh J. Shah","orcid":"https://orcid.org/0000-0002-7294-6757"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Nirmesh J. Shah","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088517679","display_name":"R Sreeraj","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R. Sreeraj","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101799872","display_name":"Neil Shah","orcid":"https://orcid.org/0000-0003-3261-8430"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neil Shah","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091143209"],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":0.8144,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80609035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"39","issue":null,"first_page":"1776","last_page":"1781"},"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":0.9998999834060669,"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":0.9984999895095825,"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/mixture-model","display_name":"Mixture model","score":0.9026412963867188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6850878000259399},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5672222375869751},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5652708411216736},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.555465817451477},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5206291079521179},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.4728803038597107},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46597716212272644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45060208439826965},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4498419761657715},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4339463412761688},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4172241687774658},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4157830476760864},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.34427958726882935}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.9026412963867188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6850878000259399},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5672222375869751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5652708411216736},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.555465817451477},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5206291079521179},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.4728803038597107},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46597716212272644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45060208439826965},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4498419761657715},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4339463412761688},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4172241687774658},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4157830476760864},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.34427958726882935},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659638","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W49412823","https://openalex.org/W142801778","https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1578200545","https://openalex.org/W1836465849","https://openalex.org/W1968869378","https://openalex.org/W2049633694","https://openalex.org/W2069883713","https://openalex.org/W2098044214","https://openalex.org/W2099471712","https://openalex.org/W2100649345","https://openalex.org/W2107076535","https://openalex.org/W2118566939","https://openalex.org/W2120605154","https://openalex.org/W2126203737","https://openalex.org/W2161476805","https://openalex.org/W2295406225","https://openalex.org/W2407281753","https://openalex.org/W2473388484","https://openalex.org/W2518172956","https://openalex.org/W2526493173","https://openalex.org/W2532494225","https://openalex.org/W2576309025","https://openalex.org/W2598392802","https://openalex.org/W2651834199","https://openalex.org/W2746457594","https://openalex.org/W2747744257","https://openalex.org/W2765628712","https://openalex.org/W2765811365","https://openalex.org/W2783781261","https://openalex.org/W2787011665","https://openalex.org/W2802304149","https://openalex.org/W2888796252","https://openalex.org/W2889042353","https://openalex.org/W2889048414","https://openalex.org/W2949117887","https://openalex.org/W2962896155","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W2963684088","https://openalex.org/W2963971656","https://openalex.org/W2964121744","https://openalex.org/W2964135678","https://openalex.org/W4320013936","https://openalex.org/W6602007935","https://openalex.org/W6605781699","https://openalex.org/W6631190155","https://openalex.org/W6634550209","https://openalex.org/W6638667902","https://openalex.org/W6685352114","https://openalex.org/W6726528559","https://openalex.org/W6728445508","https://openalex.org/W6742802039","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2129090883","https://openalex.org/W2131049662","https://openalex.org/W4287117424"],"abstract_inverted_index":{"Voice":[0,161],"Conversion":[1,162],"(VC)":[2],"requires":[3],"an":[4],"alignment":[5],"of":[6,33,41,96,110,117,149,170,194],"the":[7,12,17,22,31,39,51,64,67,80,85,107,114,125,147,150,160,177,183,187,191,195],"spectral":[8],"features":[9],"before":[10],"learning":[11],"mapping":[13],"function,":[14],"due":[15,78],"to":[16,79,93,105,131,145],"speaking":[18,81],"rate":[19],"variations":[20,83],"across":[21,73,84],"source":[23],"and":[24,138,172,190],"target":[25],"speakers.":[26,86],"To":[27],"address":[28],"this":[29,47,89],"issue,":[30],"idea":[32],"training":[34],"two":[35],"parallel":[36],"networks":[37],"with":[38,113,176],"use":[40],"speaker-independent":[42,60],"representation":[43],"was":[44],"proposed.":[45],"In":[46,87],"paper,":[48],"we":[49],"explore":[50],"unsupervised":[52],"Gaussian":[53],"Mixture":[54,153],"Model":[55],"(GMM)":[56],"posteriorgram":[57,158,181,185],"as":[58],"a":[59,94,100,133,139],"representation.":[61],"However,":[62],"in":[63],"GMM":[65,155,180,184],"posteriorgram,":[66],"same":[68],"phonetic":[69],"information":[70],"gets":[71],"spread":[72,90],"more":[74],"than":[75],"one":[76],"component":[77,112],"style":[82],"particular,":[88],"is":[91,174],"limited":[92,115],"group":[95],"neighboring":[97,118],"components":[98,119],"for":[99,186],"given":[101],"phone.":[102],"We":[103,129],"propose":[104,130],"share":[106],"posterior":[108],"probability":[109],"each":[111],"number":[116],"that":[120],"are":[121],"sorted":[122],"based":[123],"on":[124,159],"Kullback-Leibler":[126],"(KL)":[127],"divergence.":[128],"employ":[132],"Deep":[134],"Neural":[135],"Network":[136,142],"(DNN)":[137],"Generative":[140],"Adversarial":[141],"(GAN)-based":[143],"framework":[144],"measure":[146],"effectiveness":[148],"proposed":[151,178],"Inter":[152],"Weighted":[154],"(IMW":[156],"GMM)":[157],"Challenge":[163],"(VCC)":[164],"2016":[165],"database.":[166],"The":[167],"relative":[168],"improvement":[169],"13.73%,":[171],"5.25%":[173],"obtained":[175],"IMW":[179],"w.r.t.":[182],"speech":[188],"quality":[189],"speaker":[192],"similarity":[193],"converted":[196],"voices,":[197],"respectively.":[198]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}