{"id":"https://openalex.org/W4289913100","doi":"https://doi.org/10.1109/taslp.2022.3196879","title":"A Machine Speech Chain Approach for Dynamically Adaptive Lombard TTS in Static and Dynamic Noise Environments","display_name":"A Machine Speech Chain Approach for Dynamically Adaptive Lombard TTS in Static and Dynamic Noise Environments","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4289913100","doi":"https://doi.org/10.1109/taslp.2022.3196879"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3196879","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3196879","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09851526.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/ielx7/6570655/6633080/09851526.pdf","any_repository_has_fulltext":true},"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, Ikoma, Japan","Department of Science and Technology, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Department of Science and Technology, 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/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]},{"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":["Japan Advanced Institute of Science and Technology, Nomi, Japan","Department of Science and Technology, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Department of Science and Technology, 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":["Department of Science and Technology, Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Science and Technology, Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048192694"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":1.527,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.85374577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"2673","last_page":"2688"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9990000128746033,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7808913588523865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7612676620483398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7200921177864075},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5907727479934692},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4588840901851654},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4588054418563843},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.453428715467453},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4205082654953003},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.34819740056991577},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3242456316947937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22336116433143616}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7808913588523865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612676620483398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7200921177864075},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5907727479934692},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4588840901851654},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4588054418563843},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.453428715467453},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4205082654953003},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.34819740056991577},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3242456316947937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22336116433143616},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2022.3196879","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3196879","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09851526.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"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005782870","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4419","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},{"id":"pmh:oai:library.naist.jp:10061/14770","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/14770","pdf_url":null,"source":{"id":"https://openalex.org/S4377196843","display_name":"NAIST Digital Library (Nara Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I75917431","host_organization_name":"Nara Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I75917431"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3196879","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3196879","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09851526.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":[{"display_name":"Peace, Justice and strong institutions","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16"}],"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/G2363020693","display_name":null,"funder_award_id":"21H05054","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/G3670916553","display_name":null,"funder_award_id":"21H05","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4227499671","display_name":null,"funder_award_id":"KAKENHI 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/G5786340949","display_name":null,"funder_award_id":"KAKENHI Grant Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6214486782","display_name":null,"funder_award_id":"Kyoto University","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7236939988","display_name":null,"funder_award_id":"JP21H03467","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7314194600","display_name":null,"funder_award_id":"RIKEN","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7752643416","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7893352204","display_name":null,"funder_award_id":"JP21H05054","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/G8843746042","display_name":null,"funder_award_id":"JP21H0505","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335125","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98"},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4289913100.pdf","grobid_xml":"https://content.openalex.org/works/W4289913100.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W65497148","https://openalex.org/W79778379","https://openalex.org/W1548590042","https://openalex.org/W1571920584","https://openalex.org/W1716865208","https://openalex.org/W1934478182","https://openalex.org/W1970539221","https://openalex.org/W2024490156","https://openalex.org/W2032529828","https://openalex.org/W2032614435","https://openalex.org/W2032876136","https://openalex.org/W2047046272","https://openalex.org/W2049177240","https://openalex.org/W2050238139","https://openalex.org/W2058542017","https://openalex.org/W2070618467","https://openalex.org/W2083368060","https://openalex.org/W2084609288","https://openalex.org/W2105636585","https://openalex.org/W2119500623","https://openalex.org/W2133564696","https://openalex.org/W2141998673","https://openalex.org/W2151484683","https://openalex.org/W2153914468","https://openalex.org/W2401725871","https://openalex.org/W2402611215","https://openalex.org/W2404921964","https://openalex.org/W2405432219","https://openalex.org/W2592497314","https://openalex.org/W2612434969","https://openalex.org/W2747874407","https://openalex.org/W2892009249","https://openalex.org/W2898119970","https://openalex.org/W2903739847","https://openalex.org/W2963609956","https://openalex.org/W3004086395","https://openalex.org/W3009565979","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3094717326","https://openalex.org/W3095545636","https://openalex.org/W3097587372","https://openalex.org/W3100684970","https://openalex.org/W3104081910","https://openalex.org/W3114579299","https://openalex.org/W3146104336","https://openalex.org/W3156563027","https://openalex.org/W3197754566","https://openalex.org/W3202312061","https://openalex.org/W3205328248","https://openalex.org/W4200475319","https://openalex.org/W4234195863","https://openalex.org/W6603221034","https://openalex.org/W6632822233","https://openalex.org/W6677254419","https://openalex.org/W6679434410","https://openalex.org/W6712654698","https://openalex.org/W6712845745","https://openalex.org/W6737575990","https://openalex.org/W6748409065","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6783867762","https://openalex.org/W6785578985","https://openalex.org/W6802715664"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121"],"abstract_inverted_index":{"Recent":[0],"end-to-end":[1],"text-to-speech":[2],"synthesis":[3],"(TTS)":[4],"systems":[5,23,203],"have":[6],"successfully":[7],"synthesized":[8],"high-quality":[9],"speech.":[10,79],"However,":[11],"TTS":[12,45,107,123,137,175,179,185,202,220],"speech":[13,86,95,98,127,132,142,154,160,221],"intelligibility":[14,161,222],"degrades":[15],"in":[16,63,108,124,204,223],"noisy":[17,29,47,64,109],"environments":[18,110],"because":[19],"most":[20],"of":[21,77,151,174],"these":[22],"were":[24],"not":[25],"designed":[26],"to":[27,34,42,46,73,97,106,114,130,190],"handle":[28],"environments.":[30],"Several":[31],"works":[32],"attempted":[33],"address":[35],"this":[36],"problem":[37],"by":[38,84,140],"using":[39],"offline":[40,54],"fine-tuning":[41],"adapt":[43],"their":[44,70,78],"conditions.":[48,210],"Unlike":[49],"machines,":[50],"humans":[51],"never":[52],"perform":[53],"fine-tuning.":[55],"Instead,":[56],"they":[57,67],"speak":[58],"with":[59,133,180,187],"the":[60,75,85,115,146,152,159,164,192,201,219],"Lombard":[61,117,122],"effect":[62],"places,":[65],"where":[66],"dynamically":[68],"adjust":[69],"vocal":[71],"effort":[72],"improve":[74],"audibility":[76],"This":[80,100],"ability":[81],"is":[82,112],"supported":[83],"chain":[87,128],"mechanism,":[88],"which":[89],"involves":[90],"auditory":[91,147,216],"feedback":[92,148,182,189,217],"passing":[93],"from":[94],"perception":[96],"production.":[99],"paper":[101],"proposes":[102],"an":[103],"alternative":[104],"approach":[105],"that":[111,149,215],"closer":[113],"human":[116],"effect.":[118],"Specifically,":[119],"we":[120,199],"implement":[121],"a":[125],"machine":[126],"framework":[129],"synthesize":[131],"dynamic":[134,208],"adaptation.":[135],"Our":[136,211],"performs":[138],"adaptation":[139],"generating":[141],"utterances":[143],"based":[144],"on":[145],"consists":[150],"automatic":[153],"recognition":[155],"(ASR)":[156],"loss":[157],"as":[158,169],"measure":[162],"and":[163,183,207],"speech-to-noise":[165],"ratio":[166],"(SNR)":[167],"prediction":[168],"power":[170],"measurement.":[171],"Two":[172],"versions":[173],"are":[176],"investigated:":[177],"non-incremental":[178],"utterance-level":[181],"incremental":[184],"(ITTS)":[186],"short-term":[188],"reduce":[191],"delay":[193],"without":[194],"significant":[195],"performance":[196],"loss.":[197],"Furthermore,":[198],"evaluate":[200],"both":[205],"static":[206],"noise":[209],"experimental":[212],"results":[213],"show":[214],"enhanced":[218],"noise.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}