{"id":"https://openalex.org/W4372341338","doi":"https://doi.org/10.1109/icassp49357.2023.10095404","title":"Style Modeling for Multi-Speaker Articulation-to-Speech","display_name":"Style Modeling for Multi-Speaker Articulation-to-Speech","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341338","doi":"https://doi.org/10.1109/icassp49357.2023.10095404"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095404","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":"conference-paper","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/A5066878875","display_name":"Miseul Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Miseul Kim","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010663694","display_name":"Zhenyu Piao","orcid":"https://orcid.org/0009-0008-1801-4343"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Zhenyu Piao","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413513","display_name":"Ji\u2010Hyun Lee","orcid":"https://orcid.org/0000-0002-9864-5485"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihyun Lee","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101203935","display_name":"Hong-Goo Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":1.3067,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81684764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"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":0.9994000196456909,"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":0.9994000196456909,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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":0.7258704900741577},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.6978480815887451},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6758496761322021},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.643025279045105},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48846378922462463},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.430298388004303},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3356465995311737},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.08946895599365234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7258704900741577},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.6978480815887451},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6758496761322021},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.643025279045105},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48846378922462463},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.430298388004303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3356465995311737},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.08946895599365234},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095404","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1128417033","https://openalex.org/W1971596446","https://openalex.org/W1993534530","https://openalex.org/W2008120082","https://openalex.org/W2014112953","https://openalex.org/W2076104081","https://openalex.org/W2395052932","https://openalex.org/W2794490148","https://openalex.org/W2888815552","https://openalex.org/W2888917702","https://openalex.org/W2940585064","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3093377669","https://openalex.org/W3095458540","https://openalex.org/W3095801312","https://openalex.org/W3097777922","https://openalex.org/W3159506701","https://openalex.org/W3168527213","https://openalex.org/W3175752069","https://openalex.org/W4230041798","https://openalex.org/W4291824895","https://openalex.org/W6711753470","https://openalex.org/W6750489868","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6795807602","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,18,34],"neural":[6],"articulation-to-speech":[7],"(ATS)":[8],"framework":[9],"that":[10],"synthesizes":[11],"high-quality":[12],"speech":[13,32,62,105],"from":[14,33,59],"articulatory":[15,37,90],"signal":[16],"in":[17,110,117],"multi-speaker":[19],"situation.":[20],"Most":[21],"conventional":[22],"ATS":[23],"approaches":[24],"only":[25],"focus":[26],"on":[27],"modeling":[28],"contextual":[29,50],"information":[30,88],"of":[31,89,103,112],"single":[35],"speaker\u2019s":[36,43],"features.":[38],"To":[39],"explicitly":[40],"represent":[41],"each":[42],"speaking":[44],"style":[45,56,63],"as":[46,48,66],"well":[47],"the":[49,60,101,108,118],"information,":[51],"our":[52,79],"proposed":[53],"model":[54,80,98],"estimates":[55],"embeddings,":[57],"guided":[58],"essential":[61],"attributes":[64],"such":[65],"pitch":[67],"and":[68,74,86,114],"energy.":[69],"We":[70],"adopt":[71],"convolutional":[72],"layers":[73,77],"transformer-based":[75],"attention":[76],"for":[78],"to":[81,107],"fully":[82],"utilize":[83],"both":[84],"local":[85],"global":[87],"signals,":[91],"measured":[92],"by":[93],"electromagnetic":[94],"articulogra-phy":[95],"(EMA).":[96],"Our":[97],"significantly":[99],"improves":[100],"quality":[102],"synthesized":[104],"compared":[106],"baseline":[109],"terms":[111],"objective":[113],"subjective":[115],"measurements":[116],"Haskins":[119],"dataset.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}