{"id":"https://openalex.org/W4372260118","doi":"https://doi.org/10.1109/icassp49357.2023.10096128","title":"Self-Adaptive Incremental Machine Speech Chain for Lombard TTS with High-Granularity ASR Feedback in Dynamic Noise Condition","display_name":"Self-Adaptive Incremental Machine Speech Chain for Lombard TTS with High-Granularity ASR Feedback in Dynamic Noise Condition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260118","doi":"https://doi.org/10.1109/icassp49357.2023.10096128"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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","Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]},{"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/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,Japan","Japan Advanced Institute of Science and Technology, Japan","Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I177738480"]},{"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan","Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"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/A5048192694"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.3491,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.630146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9995999932289124,"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":0.9994999766349792,"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":0.8204011917114258},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.720272421836853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7164404988288879},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5560243129730225},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5086656212806702},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4735404849052429},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43542179465293884},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4345911145210266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4046041667461395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8204011917114258},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.720272421836853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7164404988288879},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5560243129730225},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5086656212806702},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4735404849052429},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43542179465293884},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4345911145210266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4046041667461395},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2024490156","https://openalex.org/W2058542017","https://openalex.org/W2083368060","https://openalex.org/W2141998673","https://openalex.org/W2401725871","https://openalex.org/W2892009249","https://openalex.org/W2938947737","https://openalex.org/W2946200149","https://openalex.org/W2962699523","https://openalex.org/W2963609956","https://openalex.org/W3008480565","https://openalex.org/W3009565979","https://openalex.org/W3033411150","https://openalex.org/W3095545636","https://openalex.org/W3097587372","https://openalex.org/W3197754566","https://openalex.org/W3198840231","https://openalex.org/W4234195863","https://openalex.org/W4289913100","https://openalex.org/W6763832098","https://openalex.org/W6778823374"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W4382701072","https://openalex.org/W2114688254"],"abstract_inverted_index":{"A":[0],"common":[1],"approach":[2],"for":[3,131,135],"text-to-speech":[4],"(TTS)":[5],"in":[6,28,40,110,148],"noisy":[7,44,137,149],"conditions":[8,150],"is":[9,13],"offline":[10],"fine-tuning,":[11],"which":[12],"generally":[14],"utilized":[15],"on":[16,47,67,83,118,152,159],"static":[17],"noises":[18],"and":[19,42,55,113,154,164],"predefined":[20],"conditions.":[21],"We":[22,116],"recently":[23],"proposed":[24,142],"a":[25,78,119,125],"self-adaptive":[26,97,120],"TTS":[27,35,98,122],"machine":[29],"speech":[30,52,70,157],"chain":[31],"inference":[32],"that":[33,61,129],"enables":[34],"to":[36],"control":[37],"its":[38],"voices":[39],"statically":[41],"dynamically":[43,136],"environments":[45],"based":[46,81,151],"auditory":[48],"feedback":[49,75,103,127],"from":[50],"automatic":[51],"recognition":[53],"(ASR)":[54],"speech-to-noise":[56],"ratio":[57],"(SNR)":[58],"recognition.":[59],"However,":[60],"study":[62],"only":[63,82],"investigated":[64],"the":[65,73,84,87,96,108,111,160],"system":[66],"synthetic":[68,153],"Lombard":[69,156],"data.":[71],"Furthermore,":[72],"ASR":[74,102],"was":[76],"at":[77,104],"lower":[79],"granularity":[80],"loss":[85],"of":[86],"positive":[88,112],"character":[89],"class.":[90],"In":[91,139],"this":[92],"paper,":[93],"we":[94],"improve":[95],"using":[99],"character-vocabulary":[100],"level":[101],"higher":[105],"granularity,":[106],"considering":[107],"losses":[109],"negative":[114],"classes.":[115],"focus":[117],"incremental":[121],"(Adapt-ITTS)":[123],"with":[124],"short-term":[126],"mechanism":[128],"aims":[130],"low":[132],"latency":[133],"adaptation":[134],"situations.":[138],"experiments,":[140],"our":[141],"Adapt-":[143],"ITTS":[144],"successfully":[145],"improved":[146],"intelligibility":[147],"natural":[155],"data":[158],"Wall":[161],"Street":[162],"Journal":[163],"Hurricane":[165],"datasets,":[166],"respectively.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}