{"id":"https://openalex.org/W3096216486","doi":"https://doi.org/10.21437/interspeech.2020-3033","title":"Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge","display_name":"Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096216486","doi":"https://doi.org/10.21437/interspeech.2020-3033","mag":"3096216486"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-3033","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5038296765","display_name":"Andros Tjandra","orcid":"https://orcid.org/0000-0003-1246-5908"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["RIKEN, Center for Advanced Intelligence Project AIP, Japan","Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan","RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038296765"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":2.5825,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.9182816,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4851","last_page":"4855"},"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":0.9995999932289124,"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":0.9994999766349792,"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/codebook","display_name":"Codebook","score":0.9152580499649048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8043252229690552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6858444213867188},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6074566841125488},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5988630652427673},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4719846844673157},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44315701723098755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38872069120407104},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08004504442214966}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.9152580499649048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043252229690552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6858444213867188},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6074566841125488},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5988630652427673},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4719846844673157},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44315701723098755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38872069120407104},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08004504442214966},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-3033","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1688345242","display_name":null,"funder_award_id":"17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4827429566","display_name":null,"funder_award_id":"Grant Numbers","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6616750388","display_name":null,"funder_award_id":"JP17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8777250574","display_name":"Research for unsupervised acoustic pattern discovery with zero resources","funder_award_id":"17K00237","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G947068629","display_name":null,"funder_award_id":"JP17K00237","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2025768430","https://openalex.org/W2120847449","https://openalex.org/W2191779130","https://openalex.org/W2547039119","https://openalex.org/W2789543585","https://openalex.org/W2906111771","https://openalex.org/W2940544976","https://openalex.org/W2963799213","https://openalex.org/W2972374322","https://openalex.org/W2972867623","https://openalex.org/W2979476256","https://openalex.org/W3125709657","https://openalex.org/W4288107125","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2014919663","https://openalex.org/W2171564668","https://openalex.org/W2110375858","https://openalex.org/W2365863649","https://openalex.org/W2367622526","https://openalex.org/W2372081722","https://openalex.org/W2377001183","https://openalex.org/W2136885550","https://openalex.org/W2369158369","https://openalex.org/W2381098171"],"abstract_inverted_index":{"In":[0],"this":[1,19],"paper,":[2],"we":[3,39,92,111],"report":[4],"our":[5],"submitted":[6],"system":[7,42,70],"for":[8,96,103],"the":[9,65,75,79,84,104,108],"ZeroSpeech":[10],"2020":[11],"challenge":[12,20],"on":[13],"Track":[14],"2019.The":[15],"main":[16,88],"theme":[17],"in":[18,58],"is":[21,91],"to":[22,35,73,117],"build":[23,40],"a":[24,41],"speech":[25,53,105],"synthesizer":[26],"without":[27],"any":[28],"textual":[29],"information":[30],"or":[31],"phonetic":[32],"labels.In":[33],"order":[34],"tackle":[36],"those":[37],"challenges,":[38],"that":[43],"must":[44],"address":[45],"two":[46],"major":[47],"components":[48],"such":[49],"as":[50],"1)":[51],"given":[52,107],"audio,":[54],"extract":[55],"subword":[56],"units":[57],"an":[59],"unsupervised":[60,97],"way":[61],"and":[62,83,100],"2)":[63],"resynthesize":[64],"audio":[66],"from":[67],"novel":[68],"speakers.The":[69],"also":[71,112],"needs":[72],"balance":[74],"codebook":[76],"performance":[77,119],"between":[78],"ABX":[80],"error":[81],"rate":[82],"bitrate":[85],"compression":[86],"rate.Our":[87],"contribution":[89],"here":[90],"proposed":[93],"Transformer-based":[94],"VQ-VAE":[95],"unit":[98],"discovery":[99],"Transformerbased":[101],"inverter":[102],"synthesis":[106],"extracted":[109],"codebook.Additionally,":[110],"explored":[113],"several":[114],"regularization":[115],"methods":[116],"improve":[118],"even":[120],"further.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}