{"id":"https://openalex.org/W2962699523","doi":"https://doi.org/10.1109/asru.2017.8268950","title":"Listening while speaking: Speech chain by deep learning","display_name":"Listening while speaking: Speech chain by deep learning","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2962699523","doi":"https://doi.org/10.1109/asru.2017.8268950","mag":"2962699523"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268950","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, 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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, 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/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":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, 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":15.4832,"has_fulltext":false,"cited_by_count":146,"citation_normalized_percentile":{"value":0.99181936,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"301","last_page":"308"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7837080955505371},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7681560516357422},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7510286569595337},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6324931979179382},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5588515996932983},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.52522873878479},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5192946791648865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5016844272613525},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4779236912727356},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.4648624360561371},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4584142863750458},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43193912506103516},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4278668463230133},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4273372292518616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39881864190101624},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.11719700694084167},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08087024092674255},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07780605554580688},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.071740061044693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837080955505371},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7681560516357422},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7510286569595337},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6324931979179382},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5588515996932983},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.52522873878479},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5192946791648865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016844272613525},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4779236912727356},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.4648624360561371},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4584142863750458},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43193912506103516},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4278668463230133},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4273372292518616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39881864190101624},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.11719700694084167},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08087024092674255},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07780605554580688},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.071740061044693},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268950","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":44,"referenced_works":["https://openalex.org/W206967138","https://openalex.org/W1514535095","https://openalex.org/W1586532344","https://openalex.org/W1600722501","https://openalex.org/W1608375737","https://openalex.org/W1810943226","https://openalex.org/W1861172732","https://openalex.org/W1902237438","https://openalex.org/W1921523184","https://openalex.org/W1935012542","https://openalex.org/W1990005915","https://openalex.org/W2042196737","https://openalex.org/W2063223471","https://openalex.org/W2078993594","https://openalex.org/W2101346879","https://openalex.org/W2102003408","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/W2327501763","https://openalex.org/W2398826216","https://openalex.org/W2422843715","https://openalex.org/W2519091744","https://openalex.org/W2546938941","https://openalex.org/W2591927543","https://openalex.org/W2604184139","https://openalex.org/W2949382160","https://openalex.org/W2963357083","https://openalex.org/W2964308564","https://openalex.org/W3210141620","https://openalex.org/W6608432165","https://openalex.org/W6630875275","https://openalex.org/W6670693114","https://openalex.org/W6675380101","https://openalex.org/W6679436768","https://openalex.org/W6696126599","https://openalex.org/W6712560600"],"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":[1,37,49,89,100,108,114,119,127,132,136,143,161,166],"close":[2],"relationship":[3],"between":[4],"speech":[5,12,42,69,102,110,151],"perception":[6,152],"and":[7,15,65,94,153],"production,":[8],"research":[9],"in":[10,79],"automatic":[11],"recognition":[13],"(ASR)":[14],"text-to-speech":[16],"synthesis":[17],"(TTS)":[18],"has":[19],"progressed":[20],"more":[21,168],"or":[22],"less":[23],"independently":[24],"without":[25],"exerting":[26],"much":[27],"mutual":[28],"influence":[29],"on":[30,36,73,88,113],"each":[31],"other.":[32],"In":[33,57,118],"human":[34,150],"communication,":[35],"other":[38],"hand,":[39],"a":[40,62,67],"closed-loop":[41,68],"chain":[43,70],"mechanism":[44],"with":[45,176],"auditory":[46],"feedback":[47],"from":[48,116],"speaker's":[50],"mouth":[51],"to":[52,84,106,125],"her":[53],"ear":[54],"is":[55,142],"crucial.":[56],"this":[58,141],"paper,":[59],"we":[60],"take":[61],"step":[63],"further":[64],"develop":[66],"model":[71,78,87,147],"based":[72,112],"deep":[74,145],"learning.":[75],"The":[76],"sequence-to-sequence":[77],"close-loop":[80],"architecture":[81],"allows":[82],"us":[83],"train":[85],"our":[86,139],"concatenation":[90],"of":[91,138],"both":[92],"labeled":[93,177],"unlabeled":[95,101],"data.":[96,178],"While":[97],"ASR":[98,122],"transcribes":[99],"features,":[103],"TTS":[104],"attempts":[105,124],"reconstruct":[107,126],"original":[109,128],"waveform":[111],"text":[115,129],"ASR.":[117],"opposite":[120],"direction,":[121],"also":[123],"transcription":[130],"given":[131],"synthesized":[133],"speech.":[134],"To":[135],"best":[137],"knowledge,":[140],"first":[144],"learning":[146],"that":[148,160,172],"integrates":[149],"production":[154],"behaviors.":[155],"Our":[156],"experimental":[157],"results":[158],"show":[159],"proposed":[162],"approach":[163],"significantly":[164],"improved":[165],"performance":[167],"than":[169],"separate":[170],"systems":[171],"were":[173],"only":[174],"trained":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":39},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":9}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}