{"id":"https://openalex.org/W4297095630","doi":"https://doi.org/10.1109/taslp.2022.3209948","title":"A Diffeomorphic Flow-Based Variational Framework for Multi-Speaker Emotion Conversion","display_name":"A Diffeomorphic Flow-Based Variational Framework for Multi-Speaker Emotion Conversion","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4297095630","doi":"https://doi.org/10.1109/taslp.2022.3209948"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3209948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3209948","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/A5101998305","display_name":"Ravi Shankar","orcid":"https://orcid.org/0000-0002-4882-3159"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ravi Shankar","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068532249","display_name":"Hsi-Wei Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsi-Wei Hsieh","raw_affiliation_strings":["Department of Applied Math and Statistics, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Applied Math and Statistics, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064933293","display_name":"Nicolas Charon","orcid":"https://orcid.org/0000-0002-6032-247X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolas Charon","raw_affiliation_strings":["Department of Applied Math and Statistics, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Applied Math and Statistics, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083233304","display_name":"Archana Venkataraman","orcid":"https://orcid.org/0000-0003-2653-5591"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Archana Venkataraman","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101998305"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.1487,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40165178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"31","issue":null,"first_page":"39","last_page":"53"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"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/regularization","display_name":"Regularization (linguistics)","score":0.661424994468689},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6510010957717896},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6393594741821289},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.6185092926025391},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5316296815872192},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5188370943069458},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4506422281265259},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4378878176212311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38842344284057617},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.1668146252632141}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.661424994468689},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6510010957717896},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6393594741821289},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.6185092926025391},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5316296815872192},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5188370943069458},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4506422281265259},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4378878176212311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38842344284057617},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.1668146252632141},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3209948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3209948","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":[{"id":"https://metadata.un.org/sdg/10","score":0.7099999785423279,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W226412370","https://openalex.org/W1522301498","https://openalex.org/W1590572162","https://openalex.org/W2006302620","https://openalex.org/W2040587156","https://openalex.org/W2062507334","https://openalex.org/W2077801020","https://openalex.org/W2095705004","https://openalex.org/W2115167851","https://openalex.org/W2118718620","https://openalex.org/W2120605154","https://openalex.org/W2128160875","https://openalex.org/W2131774270","https://openalex.org/W2152627593","https://openalex.org/W2161736993","https://openalex.org/W2170167891","https://openalex.org/W2187089797","https://openalex.org/W2436312725","https://openalex.org/W2471520273","https://openalex.org/W2517513811","https://openalex.org/W2617539464","https://openalex.org/W2766290211","https://openalex.org/W2774848319","https://openalex.org/W2786270934","https://openalex.org/W2899361462","https://openalex.org/W2944941081","https://openalex.org/W2962793481","https://openalex.org/W2962808998","https://openalex.org/W2963373786","https://openalex.org/W2963684088","https://openalex.org/W2963767194","https://openalex.org/W2972334330","https://openalex.org/W2972366998","https://openalex.org/W2973138167","https://openalex.org/W3015241559","https://openalex.org/W3025680351","https://openalex.org/W3095169545","https://openalex.org/W3097962967","https://openalex.org/W3133174221","https://openalex.org/W4390911626","https://openalex.org/W6631190155","https://openalex.org/W6635395577","https://openalex.org/W6674330103","https://openalex.org/W6677759377","https://openalex.org/W6685352114","https://openalex.org/W6714590955","https://openalex.org/W6718379498","https://openalex.org/W6738027021","https://openalex.org/W6745153919","https://openalex.org/W6746801104","https://openalex.org/W6780493881","https://openalex.org/W6787444278","https://openalex.org/W6860682759"],"related_works":["https://openalex.org/W2105321464","https://openalex.org/W2996690341","https://openalex.org/W2887774187","https://openalex.org/W2388220555","https://openalex.org/W2033178790","https://openalex.org/W3048739257","https://openalex.org/W1665563134","https://openalex.org/W2963604926","https://openalex.org/W1616881371","https://openalex.org/W1520875569"],"abstract_inverted_index":{"This":[0,116],"paper":[1],"introduces":[2,35],"a":[3,23,36,64,83,92,106],"new":[4,90],"framework":[5,13,148],"for":[6],"non-parallel":[7],"emotion":[8,104],"conversion":[9],"in":[10,125],"speech.":[11],"Our":[12,31],"is":[14,149],"based":[15],"on":[16],"two":[17],"key":[18,123],"contributions.":[19],"First,":[20],"we":[21,72,97],"propose":[22],"stochastic":[24,69],"version":[25],"of":[26,59,102,111,127],"the":[27,43,53,57,99,112],"popular":[28],"Cycle-GAN":[29,94],"model.":[30],"modified":[32],"loss":[33,70],"function":[34],"Kullback\u2013Leibler":[37],"(KL)":[38],"divergence":[39,77],"term":[40,78,88],"that":[41,74,121,145],"aligns":[42],"source":[44,113],"and":[45,108,133,140],"target":[46,103],"<italic":[47],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[48],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">data":[49],"distributions</i>":[50],"learned":[51],"by":[52],"generators,":[54],"thus":[55],"overcoming":[56],"limitations":[58],"sample-wise":[60],"generation.":[61],"By":[62],"using":[63],"variational":[65,93],"approximation":[66],"to":[67,131,143],"this":[68,89],"function,":[71],"show":[73],"our":[75,146],"KL":[76],"can":[79],"be":[80],"implemented":[81],"via":[82],"paired":[84],"density":[85],"discriminator.":[86],"We":[87,136],"architecture":[91],"(VCGAN).":[95],"Second,":[96],"model":[98],"prosodic":[100,114],"features":[101],"as":[105],"smooth":[107],"learnable":[109],"deformation":[110],"features.":[115],"approach":[117],"provides":[118],"implicit":[119],"regularization":[120],"offers":[122],"advantages":[124],"terms":[126],"better":[128],"range":[129],"alignment":[130],"unseen":[132],"out-of-distribution":[134],"speakers.":[135],"conduct":[137],"rigorous":[138],"experiments":[139],"comparative":[141],"studies":[142],"demonstrate":[144],"proposed":[147],"fairly":[150],"robust":[151],"with":[152],"high":[153],"performance":[154],"against":[155],"several":[156],"state-of-the-art":[157],"baselines.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}