{"id":"https://openalex.org/W3096207385","doi":"https://doi.org/10.21437/interspeech.2020-2034","title":"Incremental Machine Speech Chain Towards Enabling Listening While Speaking in Real-Time","display_name":"Incremental Machine Speech Chain Towards Enabling Listening While Speaking in Real-Time","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096207385","doi":"https://doi.org/10.21437/interspeech.2020-2034","mag":"3096207385"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2034","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2034","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/A5048192694","display_name":"Sashi Novitasari","orcid":"https://orcid.org/0000-0001-7467-5682"},"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":"Sashi Novitasari","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/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":false,"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/A5067528281","display_name":"Tomoya Yanagita","orcid":"https://orcid.org/0000-0001-8250-6088"},"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":"Tomoya Yanagita","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/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":"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/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":"Satoshi Nakamura","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048192694"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1372503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4372","last_page":"4376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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/T12031","display_name":"Speech and dialogue systems","score":0.9979000091552734,"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":0.9940999746322632,"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/active-listening","display_name":"Active listening","score":0.7267723083496094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7260304689407349},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.580545961856842},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37619200348854065},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12431997060775757},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09920117259025574}],"concepts":[{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7267723083496094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7260304689407349},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.580545961856842},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37619200348854065},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12431997060775757},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09920117259025574}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2034","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2034","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":[],"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":28,"referenced_works":["https://openalex.org/W7198584","https://openalex.org/W44352932","https://openalex.org/W98722733","https://openalex.org/W950853366","https://openalex.org/W1548590042","https://openalex.org/W2024490156","https://openalex.org/W2032876136","https://openalex.org/W2056890381","https://openalex.org/W2070618467","https://openalex.org/W2089629691","https://openalex.org/W2133564696","https://openalex.org/W2178654303","https://openalex.org/W2395821692","https://openalex.org/W2612434969","https://openalex.org/W2696248230","https://openalex.org/W2729190387","https://openalex.org/W2889095150","https://openalex.org/W2962699523","https://openalex.org/W2962742956","https://openalex.org/W2962826786","https://openalex.org/W2963581463","https://openalex.org/W2963609956","https://openalex.org/W2963796886","https://openalex.org/W2972356804","https://openalex.org/W2972451902","https://openalex.org/W2972895078","https://openalex.org/W2973084242","https://openalex.org/W4318717450"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969"],"abstract_inverted_index":{"Inspired":[0],"by":[1,109],"a":[2,7,50,71,116,137],"human":[3],"speech":[4,9,25,89,145],"chain":[5,10,90],"mechanism,":[6],"machine":[8,88,93,144],"framework":[11,125],"based":[12],"on":[13],"deep":[14],"learning":[15],"was":[16],"recently":[17],"proposed":[18,124],"for":[19],"the":[20,33,141],"semi-supervised":[21],"development":[22],"of":[23],"automatic":[24],"recognition":[26],"(ASR)":[27],"and":[28,67,105],"text-to-speech":[29],"synthesis":[30],"(TTS)":[31],"systems.However,":[32],"mechanism":[34],"to":[35,61,79,94,128,132,140],"listen":[36,60,95],"while":[37,96,135],"speaking":[38,97],"can":[39,59],"be":[40,77],"done":[41],"only":[42],"after":[43],"receiving":[44],"entire":[45],"input":[46],"sequences.Thus,":[47],"there":[48,69],"is":[49,70,126],"significant":[51],"delay":[52,72],"when":[53],"encountering":[54],"long":[55,133],"utterances.By":[56],"contrast,":[57],"humans":[58],"what":[62],"they":[63,75],"speak":[64],"in":[65,73,98],"real-time,":[66],"if":[68],"hearing,":[74],"won't":[76],"able":[78,127],"continue":[80],"speaking.In":[81],"this":[82],"work,":[83],"we":[84,100],"propose":[85],"an":[86],"incremental":[87,102,106],"towards":[91],"enabling":[92],"real-time.Specifically,":[99],"construct":[101],"ASR":[103],"(ISR)":[104],"TTS":[107],"(ITTS)":[108],"letting":[110],"both":[111],"systems":[112],"improve":[113],"together":[114],"through":[115],"short-term":[117],"loop.Our":[118],"experimental":[119],"results":[120],"reveal":[121],"that":[122],"our":[123],"reduce":[129],"delays":[130],"due":[131],"utterances":[134],"keeping":[136],"comparable":[138],"performance":[139],"non-incremental":[142],"basic":[143],"chain.":[146]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
