{"id":"https://openalex.org/W3096246310","doi":"https://doi.org/10.21437/interspeech.2020-2001","title":"Augmenting Images for ASR and TTS Through Single-Loop and Dual-Loop Multimodal Chain Framework","display_name":"Augmenting Images for ASR and TTS Through Single-Loop and Dual-Loop Multimodal Chain Framework","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096246310","doi":"https://doi.org/10.21437/interspeech.2020-2001","mag":"3096246310"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2001","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2001","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/A5091846449","display_name":"Johanes Effendi","orcid":"https://orcid.org/0000-0001-5755-415X"},"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":true,"raw_author_name":"Johanes Effendi","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":"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/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":["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"]}]},{"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":["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":4,"corresponding_author_ids":["https://openalex.org/A5091846449"],"corresponding_institution_ids":["https://openalex.org/I4210126580","https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.2718,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65406153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4901","last_page":"4905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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":0.996999979019165,"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":0.9847999811172485,"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":0.9803000092506409,"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/loop","display_name":"Loop (graph theory)","score":0.7980266809463501},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6500345468521118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6020547151565552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45910927653312683},{"id":"https://openalex.org/keywords/feedback-loop","display_name":"Feedback loop","score":0.4464617371559143},{"id":"https://openalex.org/keywords/dual-loop","display_name":"Dual loop","score":0.4226223826408386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3805539011955261},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20424610376358032},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17999643087387085},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.0666714608669281},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06583467125892639},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.05888769030570984}],"concepts":[{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.7980266809463501},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6500345468521118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6020547151565552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45910927653312683},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.4464617371559143},{"id":"https://openalex.org/C2779691726","wikidata":"https://www.wikidata.org/wiki/Q5310214","display_name":"Dual loop","level":3,"score":0.4226223826408386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3805539011955261},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20424610376358032},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17999643087387085},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0666714608669281},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06583467125892639},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.05888769030570984}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2001","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2001","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/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/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/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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1630959083","https://openalex.org/W2109135012","https://openalex.org/W2119775030","https://openalex.org/W2137010615","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2546938941","https://openalex.org/W2586850765","https://openalex.org/W2612434969","https://openalex.org/W2803775694","https://openalex.org/W2890952074","https://openalex.org/W2951939904","https://openalex.org/W2952746495","https://openalex.org/W2962699523","https://openalex.org/W2963295405","https://openalex.org/W2963373786","https://openalex.org/W2963444790","https://openalex.org/W2963581463","https://openalex.org/W2963796886","https://openalex.org/W2963966654","https://openalex.org/W2964048171","https://openalex.org/W3009035583"],"related_works":["https://openalex.org/W2375499102","https://openalex.org/W3084132679","https://openalex.org/W2381125525","https://openalex.org/W1965937483","https://openalex.org/W4301401229","https://openalex.org/W2007705401","https://openalex.org/W2290436929","https://openalex.org/W4281772681","https://openalex.org/W1991639860","https://openalex.org/W2009135099"],"abstract_inverted_index":{"Previous":[0],"research":[1],"has":[2],"proposed":[3],"a":[4,31,44,66],"machine":[5,55,132],"speech":[6,11,36,82,124,159],"chain":[7,56,133,169],"to":[8,18,26,60,102,175],"enable":[9],"automatic":[10],"recognition":[12],"(ASR)":[13],"and":[14,25,37,97,139,149,153,166,173],"text-to-speech":[15],"synthesis":[16],"(TTS)":[17],"assist":[19],"each":[20],"other":[21],"in":[22],"semi-supervised":[23],"learning":[24],"avoid":[27],"the":[28,63,92,113,130,141],"need":[29,64],"for":[30,65,147],"large":[32,45,67],"amount":[33,46,68],"of":[34,47,69,115,143],"paired":[35],"text":[38,84],"data.However,":[39],"that":[40,107,163],"framework":[41,89,117,134],"still":[42],"requires":[43],"unpaired":[48,70],"(speech":[49],"or":[50,76,83],"text)":[51],"data.A":[52],"prototype":[53],"multimodal":[54,131,168],"was":[57,100,118],"then":[58],"explored":[59],"further":[61],"reduce":[62],"data,":[71],"which":[72],"could":[73],"improve":[74,176],"ASR":[75,148,172],"TTS":[77,150,174],"even":[78],"when":[79],"no":[80],"more":[81],"data":[85,146],"were":[86,108],"available.Unfortunately,":[87],"this":[88,116,126],"relied":[90],"on":[91,156],"image":[93,136,145],"retrieval":[94],"(IR)":[95],"model,":[96],"thus":[98],"it":[99],"limited":[101],"handling":[103],"only":[104,119],"those":[105],"images":[106],"already":[109],"known":[110],"during":[111],"training.Furthermore,":[112],"performance":[114,178],"investigated":[120],"with":[121,135],"single-speaker":[122],"artificial":[123],"data.In":[125],"study,":[127],"we":[128],"revamp":[129],"generation":[137],"(IG)":[138],"investigate":[140],"possibility":[142],"augmenting":[144],"using":[151,179],"single-loop":[152,165],"dual-loop":[154,167],"architectures":[155],"multispeaker":[157],"natural":[158],"data.Experimental":[160],"results":[161],"revealed":[162],"both":[164],"frameworks":[170],"enabled":[171],"their":[177],"an":[180],"image-only":[181],"dataset.":[182]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
