{"id":"https://openalex.org/W4319862691","doi":"https://doi.org/10.1109/slt54892.2023.10023432","title":"Distilling Sequence-to-Sequence Voice Conversion Models for Streaming Conversion Applications","display_name":"Distilling Sequence-to-Sequence Voice Conversion Models for Streaming Conversion Applications","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862691","doi":"https://doi.org/10.1109/slt54892.2023.10023432"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023432","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023432","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5106710403","display_name":"Kou Tanaka","orcid":"https://orcid.org/0009-0003-7107-607X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kou Tanaka","raw_affiliation_strings":["NTT Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020693766","display_name":"Takuhiro Kaneko","orcid":"https://orcid.org/0009-0000-8016-5144"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuhiro Kaneko","raw_affiliation_strings":["NTT Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101792863","display_name":"Shogo Seki","orcid":"https://orcid.org/0000-0001-8284-188X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shogo Seki","raw_affiliation_strings":["NTT Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5106710403"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.2261,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.3539823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"30","issue":null,"first_page":"1022","last_page":"1028"},"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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":0.7322060465812683},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6768596172332764},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6723089814186096},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6185075044631958},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.47060689330101013},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44281086325645447},{"id":"https://openalex.org/keywords/sequential-pattern-mining","display_name":"Sequential Pattern Mining","score":0.4358879327774048},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4181787073612213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.411832332611084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4067627787590027},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13594448566436768},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10306575894355774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322060465812683},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6768596172332764},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6723089814186096},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6185075044631958},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.47060689330101013},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44281086325645447},{"id":"https://openalex.org/C149490388","wikidata":"https://www.wikidata.org/wiki/Q1718507","display_name":"Sequential Pattern Mining","level":2,"score":0.4358879327774048},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4181787073612213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.411832332611084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4067627787590027},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13594448566436768},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10306575894355774},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023432","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023432","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"},{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1965255698","https://openalex.org/W2017742648","https://openalex.org/W2023694213","https://openalex.org/W2025700375","https://openalex.org/W2294038178","https://openalex.org/W2752796333","https://openalex.org/W2897353073","https://openalex.org/W2899877258","https://openalex.org/W2945478979","https://openalex.org/W2962780374","https://openalex.org/W2962788625","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W2972970915","https://openalex.org/W3015645837","https://openalex.org/W3034420534","https://openalex.org/W3034729383","https://openalex.org/W3083776549","https://openalex.org/W3092028330","https://openalex.org/W3096518646","https://openalex.org/W3099078140","https://openalex.org/W3113687514","https://openalex.org/W3156592906","https://openalex.org/W3161873870","https://openalex.org/W6631190155","https://openalex.org/W6745415975","https://openalex.org/W6762533536","https://openalex.org/W6779469704","https://openalex.org/W6783867762","https://openalex.org/W6784418856"],"related_works":["https://openalex.org/W2355862304","https://openalex.org/W2356108042","https://openalex.org/W2030250808","https://openalex.org/W2376796979","https://openalex.org/W2379418341","https://openalex.org/W2380054981","https://openalex.org/W2393110101","https://openalex.org/W2362264899","https://openalex.org/W2370878229","https://openalex.org/W2983146142"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,7,29,43,46,51],"method":[4],"for":[5,99],"distilling":[6],"recurrent-based":[8,70],"sequence-to-sequence":[9],"(S2S)":[10],"voice":[11],"conversion":[12,26,40],"(VC)":[13],"model.":[14],"Although":[15],"the":[16,39,66,84,109,119],"performance":[17,112],"of":[18,86,115],"recent":[19,59],"VCs":[20],"is":[21,27,77,105],"becoming":[22],"higher":[23],"quality,":[24],"streaming":[25,37],"still":[28],"challenge":[30,76],"when":[31],"considering":[32],"practical":[33],"applications.":[34],"To":[35],"achieve":[36],"VC,":[38],"model":[41,122],"needs":[42],"streamable":[44,120],"structure,":[45],"causal":[47,87],"layer":[48],"rather":[49],"than":[50],"non-causal":[52],"layer.":[53],"Motivated":[54],"by":[55],"this":[56],"constraint":[57],"and":[58],"advances":[60],"in":[61,113],"S2S":[62],"learning,":[63],"we":[64],"apply":[65],"teacher-student":[67],"framework":[68],"to":[69,79,83,107],"S2S-":[71],"VC":[72],"models.":[73],"A":[74],"major":[75],"how":[78],"minimize":[80],"degradation":[81],"due":[82],"use":[85],"layers":[88],"which":[89],"masks":[90],"future":[91],"input":[92],"information.":[93],"Experimental":[94],"evaluations":[95,117],"show":[96],"that":[97],"except":[98],"male-to-female":[100],"speaker":[101],"conversion,":[102],"our":[103],"approach":[104],"able":[106],"maintain":[108],"teacher":[110],"model's":[111],"terms":[114],"subjective":[116],"despite":[118],"student":[121],"structure.":[123],"Audio":[124],"samples":[125],"can":[126],"be":[127],"accessed":[128],"on":[129],"http://www.kecl.ntt.co.jp/people/tanaka.ko/projects/dists2svc.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}