{"id":"https://openalex.org/W2989985842","doi":"https://doi.org/10.1109/taslp.2019.2955289","title":"Learning Structured Sparse Representations for Voice Conversion","display_name":"Learning Structured Sparse Representations for Voice Conversion","publication_year":2019,"publication_date":"2019-11-22","ids":{"openalex":"https://openalex.org/W2989985842","doi":"https://doi.org/10.1109/taslp.2019.2955289","mag":"2989985842"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2955289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2955289","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/A5058886181","display_name":"Shaojin Ding","orcid":"https://orcid.org/0000-0002-2108-3111"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaojin Ding","raw_affiliation_strings":["Department of Computer Science and Engineering, Texas A&M University, College Station, USA"],"raw_orcid":"https://orcid.org/0000-0002-2108-3111","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University, College Station, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078020198","display_name":"Guanlong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanlong Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Texas A&M University, College Station, USA"],"raw_orcid":"https://orcid.org/0000-0002-6059-4053","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University, College Station, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077682246","display_name":"Christopher Liberatore","orcid":"https://orcid.org/0000-0002-5871-0596"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Liberatore","raw_affiliation_strings":["Department of Computer Science and Engineering, Texas A&M University, College Station, USA"],"raw_orcid":"https://orcid.org/0000-0002-5871-0596","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University, College Station, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062423099","display_name":"Ricardo Guti\u00e9rrez\u2010Osuna","orcid":"https://orcid.org/0000-0003-2817-2085"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ricardo Gutierrez-Osuna","raw_affiliation_strings":["Department of Computer Science and Engineering, Texas A&M University, College Station, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University, College Station, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3015,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85997167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"343","last_page":"354"},"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":0.9987000226974487,"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":0.9986000061035156,"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":0.4175669550895691},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3928462564945221},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3847256600856781},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.3584057092666626},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.35450074076652527},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3377148509025574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4175669550895691},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3928462564945221},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3847256600856781},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3584057092666626},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35450074076652527},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3377148509025574},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2955289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2955289","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":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W33214042","https://openalex.org/W33533989","https://openalex.org/W95152782","https://openalex.org/W116902681","https://openalex.org/W122926584","https://openalex.org/W147600081","https://openalex.org/W1497745584","https://openalex.org/W1509691205","https://openalex.org/W1513358034","https://openalex.org/W1808881044","https://openalex.org/W1965912016","https://openalex.org/W1970554427","https://openalex.org/W1977362459","https://openalex.org/W1991682319","https://openalex.org/W1994309289","https://openalex.org/W2001987918","https://openalex.org/W2004299580","https://openalex.org/W2005876975","https://openalex.org/W2017425464","https://openalex.org/W2017742648","https://openalex.org/W2053090063","https://openalex.org/W2061278248","https://openalex.org/W2063978378","https://openalex.org/W2086796102","https://openalex.org/W2096072446","https://openalex.org/W2100556411","https://openalex.org/W2105160541","https://openalex.org/W2112447569","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2124331435","https://openalex.org/W2127218421","https://openalex.org/W2137937911","https://openalex.org/W2138019504","https://openalex.org/W2143076222","https://openalex.org/W2144139079","https://openalex.org/W2156142001","https://openalex.org/W2157412983","https://openalex.org/W2157639439","https://openalex.org/W2160988001","https://openalex.org/W2165363188","https://openalex.org/W2168446235","https://openalex.org/W2175027794","https://openalex.org/W2285479626","https://openalex.org/W2292984643","https://openalex.org/W2400588950","https://openalex.org/W2471520273","https://openalex.org/W2509534099","https://openalex.org/W2512087624","https://openalex.org/W2518172956","https://openalex.org/W2518406046","https://openalex.org/W2519648275","https://openalex.org/W2532494225","https://openalex.org/W2560169219","https://openalex.org/W2562848127","https://openalex.org/W2675443237","https://openalex.org/W2747744257","https://openalex.org/W2752796333","https://openalex.org/W2758785877","https://openalex.org/W2785608393","https://openalex.org/W2888922217","https://openalex.org/W2888968073","https://openalex.org/W2888982879","https://openalex.org/W2890402938","https://openalex.org/W2890843704","https://openalex.org/W2963618559","https://openalex.org/W2963799213","https://openalex.org/W2964069186","https://openalex.org/W3099503819","https://openalex.org/W6601318844","https://openalex.org/W6601370681","https://openalex.org/W6603838645","https://openalex.org/W6604828220","https://openalex.org/W6604904840","https://openalex.org/W6605949115","https://openalex.org/W6629935912","https://openalex.org/W6676727762","https://openalex.org/W6678683371","https://openalex.org/W6678914141","https://openalex.org/W6683265229","https://openalex.org/W6683778382","https://openalex.org/W6684865402","https://openalex.org/W6697163159","https://openalex.org/W6713218866","https://openalex.org/W6745117592"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2931662336","https://openalex.org/W2077865380","https://openalex.org/W2134894512","https://openalex.org/W2053487507","https://openalex.org/W2765597752","https://openalex.org/W2083375246","https://openalex.org/W2067108088","https://openalex.org/W2085372204","https://openalex.org/W4391301621"],"abstract_inverted_index":{"Sparse-coding":[0],"techniques":[1],"for":[2],"voice":[3,210],"conversion":[4],"assume":[5],"that":[6,16,26,44,68,87,100,137,148,162,191,215],"an":[7],"utterance":[8],"can":[9],"be":[10,106],"decomposed":[11],"into":[12,93],"a":[13,22,63,82,96,111,131,157,181],"sparse":[14,46],"code":[15,47],"only":[17],"carries":[18],"linguistic":[19],"contents,":[20],"and":[21,34,95,147,187],"dictionary":[23,92],"of":[24,73,78,114,139,177,201],"atoms":[25,89,109],"captures":[27,218],"the":[28,45,70,74,91,121,127,140,198,202,207,216,224],"speakers'":[29],"characteristics.":[30],"However,":[31],"conventional":[32],"dictionary-construction":[33],"sparse-coding":[35],"algorithms":[36],"rarely":[37],"meet":[38],"this":[39,59],"assumption.":[40],"The":[41],"result":[42],"is":[43,48],"no":[49],"longer":[50],"speaker-independent,":[51],"which":[52],"leads":[53,152],"to":[54,105,125,153],"lower":[55],"voice-conversion":[56,195],"performance.":[57],"In":[58,130,156,180],"paper,":[60],"we":[61,160,213],"propose":[62],"Cluster-Structured":[64,83],"Sparse":[65],"Representation":[66],"(CSSR)":[67],"improves":[69],"speaker":[71,145],"independence":[72],"representations.":[75],"CSSR":[76,142,163,192,217],"consists":[77],"two":[79,141],"complementary":[80],"components:":[81],"Dictionary":[84],"Learning":[85],"module":[86],"groups":[88],"in":[90,223],"clusters,":[94],"Cluster-Selective":[97],"Objective":[98],"Function":[99],"encourages":[101],"each":[102,138],"speech":[103,178,204,225],"frame":[104],"represented":[107],"by":[108,173],"from":[110,185],"small":[112],"number":[113],"clusters.":[115],"We":[116],"conducted":[117],"four":[118],"experiments":[119],"on":[120],"CMU":[122],"ARCTIC":[123],"corpus":[124],"evaluate":[126],"proposed":[128],"method.":[129],"first":[132],"ablation":[133],"study,":[134],"results":[135,184],"show":[136,190,214],"components":[143,151],"enhances":[144],"independence,":[146],"combining":[149],"both":[150],"further":[154],"improvements.":[155],"second":[158],"experiment,":[159,183],"find":[161],"uses":[164],"increasingly":[165],"larger":[166],"dictionaries":[167],"more":[168],"efficiently":[169],"than":[170],"phoneme-based":[171],"representations":[172],"allowing":[174],"finer-grained":[175],"decompositions":[176],"sounds.":[179],"third":[182],"objective":[186],"subjective":[188],"measurements":[189],"outperforms":[193],"prior":[194],"methods,":[196],"improving":[197],"acoustic":[199],"quality":[200],"synthesized":[203],"while":[205],"retaining":[206],"target":[208],"speaker's":[209],"identity.":[211],"Finally,":[212],"latent":[219],"(i.e.,":[220],"phonetic)":[221],"information":[222],"signal.":[226]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}