{"id":"https://openalex.org/W2882976384","doi":"https://doi.org/10.1109/taslp.2018.2860682","title":"Structured Sparse Spectral Transforms and Structural Measures for Voice Conversion","display_name":"Structured Sparse Spectral Transforms and Structural Measures for Voice Conversion","publication_year":2018,"publication_date":"2018-07-27","ids":{"openalex":"https://openalex.org/W2882976384","doi":"https://doi.org/10.1109/taslp.2018.2860682","mag":"2882976384","pmid":"https://pubmed.ncbi.nlm.nih.gov/31984214"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2860682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2860682","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6980218","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033518479","display_name":"Yunxin Zhao","orcid":"https://orcid.org/0000-0001-5511-3692"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunxin Zhao","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211 USA","Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211 USA","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086236955","display_name":"Mili Kuruvilla-Dugdale","orcid":"https://orcid.org/0000-0001-7900-2364"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mili Kuruvilla-Dugdale","raw_affiliation_strings":["Department of Communication Science and Disorders, University of Missouri, Columbia, MO 65211 USA","Department of Communication Science and Disorders, University of Missouri, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Communication Science and Disorders, University of Missouri, Columbia, MO 65211 USA","institution_ids":[]},{"raw_affiliation_string":"Department of Communication Science and Disorders, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028632429","display_name":"Minguang Song","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minguang Song","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211 USA","Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211 USA","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033518479"],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":null,"apc_paid":null,"fwci":1.156,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7927468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"26","issue":"12","first_page":"2267","last_page":"2276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9954000115394592,"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":0.5998912453651428},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5866578817367554},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5706474781036377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5332175493240356},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5266449451446533},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.4989013671875},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44377368688583374},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43498510122299194},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.4264869689941406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3836413025856018},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35619229078292847},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3267357647418976},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.159014493227005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5998912453651428},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5866578817367554},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5706474781036377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5332175493240356},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5266449451446533},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.4989013671875},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44377368688583374},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43498510122299194},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.4264869689941406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3836413025856018},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35619229078292847},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3267357647418976},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.159014493227005},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2018.2860682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2860682","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"},{"id":"pmid:31984214","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31984214","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"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":null},{"id":"pmh:oai:pubmedcentral.nih.gov:6980218","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6980218","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:6980218","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6980218","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2852783149","display_name":null,"funder_award_id":"DC016383","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6546696252","display_name":null,"funder_award_id":"R15","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W11066910","https://openalex.org/W1533771558","https://openalex.org/W1578856370","https://openalex.org/W1963778986","https://openalex.org/W1965912016","https://openalex.org/W1975900269","https://openalex.org/W1977362459","https://openalex.org/W2047068213","https://openalex.org/W2053313164","https://openalex.org/W2105160541","https://openalex.org/W2105698384","https://openalex.org/W2110118271","https://openalex.org/W2116257577","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2120731853","https://openalex.org/W2121387787","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2128413412","https://openalex.org/W2131062138","https://openalex.org/W2133665775","https://openalex.org/W2141998673","https://openalex.org/W2156142001","https://openalex.org/W2165674530","https://openalex.org/W2165899180","https://openalex.org/W2169652224","https://openalex.org/W2294351487","https://openalex.org/W2389245149","https://openalex.org/W2402356521","https://openalex.org/W2408732577","https://openalex.org/W2473388484","https://openalex.org/W2518172956","https://openalex.org/W2699202114","https://openalex.org/W2733416080","https://openalex.org/W6600448489","https://openalex.org/W6679486525","https://openalex.org/W6696767757","https://openalex.org/W6713985435"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W34555840"],"abstract_inverted_index":{"We":[0,49,88],"investigate":[1,90],"a":[2,26,59,65,71,157],"structured":[3,85],"sparse":[4,86],"spectral":[5,17,94,123,130],"transform":[6,28,72],"method":[7,155],"for":[8,30,103],"voice":[9,186],"conversion":[10],"(VC)":[11],"to":[12,44,63,83,165,188],"perform":[13],"frequency":[14],"warping":[15],"and":[16,74,95,98,132,135,168,184],"shaping":[18],"simultaneously":[19],"on":[20,110,143],"high-dimensional":[21],"(D)":[22],"STRAIGHT":[23],"spectra.":[24],"Learning":[25],"large":[27],"matrix":[29,38,80],"high-D":[31],"data":[32],"often":[33],"results":[34,142],"in":[35,47,70,122,127,169,182,185],"an":[36],"overfit":[37],"with":[39,171],"low":[40],"sparsity,":[41],"which":[42],"leads":[43],"muffled":[45],"speech":[46,106],"VC.":[48],"address":[50],"this":[51],"problem":[52],"by":[53,78],"using":[54],"the":[55,120,136,152,178],"frequency-warping":[56],"characteristic":[57],"of":[58,67,93,113,161],"source-target":[60],"speaker":[61,115],"pair":[62],"define":[64],"region":[66],"support":[68],"(ROS)":[69],"matrix,":[73],"further":[75],"optimize":[76],"it":[77,176],"nonnegative":[79],"factorization":[81],"(NMF)":[82],"obtain":[84],"transform.":[87],"also":[89],"structural":[91,137],"measures":[92,138],"temporal":[96],"covariance":[97],"variance":[99],"at":[100],"different":[101],"scales":[102],"assessing":[104],"VC":[105,154,174],"quality.":[107],"Our":[108,146],"experiments":[109],"ARCTIC":[111],"dataset":[112],"12":[114],"pairs":[116],"show":[117,150],"that":[118,151],"embedding":[119],"ROS":[121],"transforms":[124],"offers":[125],"flexibility":[126],"tradeoffs":[128],"between":[129],"distortion":[131],"structure":[133],"preservation,":[134],"provide":[139],"quantitatively":[140],"reasonable":[141],"converted":[144],"speech.":[145],"subjective":[147],"listening":[148],"tests":[149],"proposed":[153],"achieves":[156],"mean":[158],"opinion":[159],"score":[160],"\"very":[162],"good\"":[163],"relative":[164],"natural":[166],"speech,":[167],"comparison":[170],"three":[172],"other":[173],"methods,":[175],"is":[177],"most":[179],"preferred":[180],"one":[181],"naturalness":[183],"similarity":[187],"target":[189],"speakers.":[190]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}