{"id":"https://openalex.org/W3009565979","doi":"https://doi.org/10.1109/taslp.2020.2977776","title":"Machine Speech Chain","display_name":"Machine Speech Chain","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3009565979","doi":"https://doi.org/10.1109/taslp.2020.2977776","mag":"3009565979"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2977776","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2977776","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09020132.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09020132.pdf","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":["Center for Advanced Intelligence Project AIP, Nara Institute of Science and Technology, Japan and RIKEN, Ikoma, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1246-5908","affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project AIP, Nara Institute of Science and Technology, Japan and RIKEN, Ikoma, 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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Center for Advanced Intelligence Project AIP, Nara Institute of Science and Technology, Japan and RIKEN, Ikoma, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5509-8963","affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project AIP, Nara Institute of Science and Technology, Japan and RIKEN, Ikoma, 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/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":["Center for Advanced Intelligence Project AIP, Nara Institute of Science and Technology, Japan and RIKEN, Ikoma, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6956-3803","affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project AIP, Nara Institute of Science and Technology, Japan and RIKEN, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"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":2.8537,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.92400046,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"976","last_page":"989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.8460675477981567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7767124176025391},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7330649495124817},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.5579179525375366},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5445102453231812},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.504114031791687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49776485562324524},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.4506981670856476},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4490460157394409},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44833144545555115},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4364660382270813},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.42716076970100403},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40918874740600586},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4018867611885071},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06992295384407043},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06988099217414856},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06736722588539124}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8460675477981567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767124176025391},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7330649495124817},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.5579179525375366},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5445102453231812},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.504114031791687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49776485562324524},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.4506981670856476},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4490460157394409},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44833144545555115},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4364660382270813},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.42716076970100403},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40918874740600586},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4018867611885071},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06992295384407043},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06988099217414856},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06736722588539124},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/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.2020.2977776","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2977776","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09020132.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1109/taslp.2020.2977776","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2977776","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09020132.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"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/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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3009565979.pdf","grobid_xml":"https://content.openalex.org/works/W3009565979.grobid-xml"},"referenced_works_count":96,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1600722501","https://openalex.org/W1630959083","https://openalex.org/W1821462560","https://openalex.org/W1861172732","https://openalex.org/W1902237438","https://openalex.org/W1921523184","https://openalex.org/W1924770834","https://openalex.org/W1935012542","https://openalex.org/W1990005915","https://openalex.org/W2024490156","https://openalex.org/W2039057510","https://openalex.org/W2063223471","https://openalex.org/W2064675550","https://openalex.org/W2078993594","https://openalex.org/W2096733369","https://openalex.org/W2101261946","https://openalex.org/W2101346879","https://openalex.org/W2102003408","https://openalex.org/W2106053110","https://openalex.org/W2115040572","https://openalex.org/W2120847449","https://openalex.org/W2128160875","https://openalex.org/W2130942839","https://openalex.org/W2133129980","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2150658333","https://openalex.org/W2157331557","https://openalex.org/W2168249605","https://openalex.org/W2242818861","https://openalex.org/W2327501763","https://openalex.org/W2331128040","https://openalex.org/W2396709924","https://openalex.org/W2398826216","https://openalex.org/W2519091744","https://openalex.org/W2526425061","https://openalex.org/W2546938941","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2591927543","https://openalex.org/W2612434969","https://openalex.org/W2884852625","https://openalex.org/W2889213362","https://openalex.org/W2889519245","https://openalex.org/W2940200615","https://openalex.org/W2945078028","https://openalex.org/W2949382160","https://openalex.org/W2952165242","https://openalex.org/W2952711665","https://openalex.org/W2962759037","https://openalex.org/W2962826786","https://openalex.org/W2963216553","https://openalex.org/W2963357083","https://openalex.org/W2963609956","https://openalex.org/W2963739817","https://openalex.org/W2964167449","https://openalex.org/W2964281804","https://openalex.org/W2964308564","https://openalex.org/W2970971581","https://openalex.org/W2972889948","https://openalex.org/W2973086555","https://openalex.org/W3008480565","https://openalex.org/W3099206234","https://openalex.org/W3210141620","https://openalex.org/W4234330420","https://openalex.org/W4295312788","https://openalex.org/W6630875275","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6636599907","https://openalex.org/W6638523607","https://openalex.org/W6640185926","https://openalex.org/W6640212811","https://openalex.org/W6670693114","https://openalex.org/W6675380101","https://openalex.org/W6675751002","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6687506355","https://openalex.org/W6690026940","https://openalex.org/W6696126599","https://openalex.org/W6702130928","https://openalex.org/W6712560600","https://openalex.org/W6729383884","https://openalex.org/W6729448088","https://openalex.org/W6730091202","https://openalex.org/W6734815144","https://openalex.org/W6736996214","https://openalex.org/W6737575990","https://openalex.org/W6762242920","https://openalex.org/W6766978945","https://openalex.org/W6917585676","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W4245668640","https://openalex.org/W2388979876","https://openalex.org/W4206187606","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2610232577","https://openalex.org/W205537210"],"abstract_inverted_index":{"Despite":[0],"the":[1,34,46,87,98,106,112,117,125,130,134,141,159],"close":[2],"relationship":[3],"between":[4],"speech":[5,12,39,67,100,108,149],"perception":[6,150],"and":[7,15,62,92,151],"production,":[8],"research":[9],"in":[10,77],"automatic":[11],"recognition":[13],"(ASR)":[14],"text-to-speech":[16],"synthesis":[17],"(TTS)":[18],"has":[19],"progressed":[20],"more":[21],"or":[22],"less":[23],"independently":[24],"without":[25],"exerting":[26],"much":[27],"mutual":[28],"influence.":[29],"In":[30,54,116],"human":[31,148],"communication,":[32],"on":[33,71,86,111],"other":[35],"hand,":[36],"a":[37,59,64],"closed-loop":[38,65,78],"chain":[40,68],"mechanism":[41],"with":[42,174],"auditory":[43],"feedback":[44],"from":[45,114,167],"speaker's":[47],"mouth":[48],"to":[49,82,104,123],"her":[50],"ear":[51],"is":[52,140],"crucial.":[53],"this":[55,139],"paper,":[56],"we":[57],"take":[58],"step":[60],"further":[61],"develop":[63],"machine":[66],"model":[69,76,85],"based":[70,110],"deep":[72,143],"learning.":[73],"The":[74],"sequence-to-sequence":[75],"architecture":[79],"allows":[80],"us":[81],"train":[83],"our":[84,137],"concatenation":[88],"of":[89,136],"both":[90],"labeled":[91,175],"unlabeled":[93,99],"data.":[94,176],"While":[95],"ASR":[96,120],"transcribes":[97],"features,":[101],"TTS":[102],"attempts":[103,122],"reconstruct":[105,124],"original":[107,126],"waveform":[109],"text":[113,127],"ASR.":[115],"opposite":[118],"direction,":[119],"also":[121],"transcription":[128],"given":[129],"synthesized":[131],"speech.":[132],"To":[133],"best":[135],"knowledge,":[138],"first":[142],"learning":[144],"framework":[145],"that":[146,158,166,170],"integrates":[147],"production":[152],"behaviors.":[153],"Our":[154],"experimental":[155],"results":[156],"show":[157],"proposed":[160],"approach":[161],"significantly":[162],"improved":[163],"performance":[164],"over":[165],"separate":[168],"systems":[169],"were":[171],"only":[172],"trained":[173]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}