{"id":"https://openalex.org/W3159506701","doi":"https://doi.org/10.1109/iscas51556.2021.9401485","title":"EMA2S: An End-to-End Multimodal Articulatory-to-Speech System","display_name":"EMA2S: An End-to-End Multimodal Articulatory-to-Speech System","publication_year":2021,"publication_date":"2021-04-27","ids":{"openalex":"https://openalex.org/W3159506701","doi":"https://doi.org/10.1109/iscas51556.2021.9401485","mag":"3159506701"},"language":"en","primary_location":{"id":"doi:10.1109/iscas51556.2021.9401485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5100428119","display_name":"Yu\u2010Wen Chen","orcid":"https://orcid.org/0000-0002-4335-7574"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu-Wen Chen","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071855826","display_name":"Kuo-Hsuan Hung","orcid":"https://orcid.org/0009-0007-0974-4873"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuo-Hsuan Hung","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033696869","display_name":"Shang-Yi Chuang","orcid":"https://orcid.org/0000-0002-8824-096X"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shang-Yi Chuang","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049434293","display_name":"Jonathan H. Sherman","orcid":"https://orcid.org/0000-0001-9482-3988"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jonathan Sherman","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["JP","TW"],"is_corresponding":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Japan","Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100428119"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":1.0665,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76166329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/T11309","display_name":"Music 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/spectrogram","display_name":"Spectrogram","score":0.9199862480163574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7674899101257324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7503563165664673},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6480329632759094},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.512738823890686},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5046406984329224},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4433276355266571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3942223787307739},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10125908255577087}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9199862480163574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7674899101257324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503563165664673},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6480329632759094},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.512738823890686},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5046406984329224},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4433276355266571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3942223787307739},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10125908255577087},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas51556.2021.9401485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W178045984","https://openalex.org/W208520372","https://openalex.org/W1552314771","https://openalex.org/W1580606264","https://openalex.org/W1647671624","https://openalex.org/W1998676560","https://openalex.org/W2005522781","https://openalex.org/W2018363392","https://openalex.org/W2019977809","https://openalex.org/W2023407680","https://openalex.org/W2049686551","https://openalex.org/W2067517374","https://openalex.org/W2068056889","https://openalex.org/W2099471712","https://openalex.org/W2107860279","https://openalex.org/W2141998673","https://openalex.org/W2184188583","https://openalex.org/W2395052932","https://openalex.org/W2406785943","https://openalex.org/W2408688265","https://openalex.org/W2419247625","https://openalex.org/W2471520273","https://openalex.org/W2508425411","https://openalex.org/W2519091744","https://openalex.org/W2528578439","https://openalex.org/W2569953749","https://openalex.org/W2788241093","https://openalex.org/W2790713205","https://openalex.org/W2888815552","https://openalex.org/W2963667133","https://openalex.org/W2964193438","https://openalex.org/W2972443522","https://openalex.org/W2983423850","https://openalex.org/W2991251958","https://openalex.org/W2994715919","https://openalex.org/W3015338123","https://openalex.org/W3015707856","https://openalex.org/W3015721889","https://openalex.org/W3090528452","https://openalex.org/W3095253811","https://openalex.org/W3096028031","https://openalex.org/W3096567388","https://openalex.org/W3099932294","https://openalex.org/W3102334822","https://openalex.org/W3154451338","https://openalex.org/W4320013936","https://openalex.org/W6607196876","https://openalex.org/W6608480465","https://openalex.org/W6636915900","https://openalex.org/W6683590716","https://openalex.org/W6686207219","https://openalex.org/W6711753470","https://openalex.org/W6714016741","https://openalex.org/W6771070734","https://openalex.org/W6775933407","https://openalex.org/W6780226713","https://openalex.org/W6783904828","https://openalex.org/W6784075877"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Synthesized":[0],"speech":[1,40],"from":[2],"articulatory":[3,37],"movements":[4,38],"can":[5,92],"have":[6],"real-world":[7],"use":[8,43],"for":[9],"patients":[10],"with":[11,48],"vocal":[12],"cord":[13],"disorders,":[14],"situations":[15],"requiring":[16],"silent":[17],"speech,":[18],"or":[19],"in":[20,71],"high-noise":[21],"environments.":[22],"In":[23],"this":[24],"work,":[25],"we":[26],"present":[27],"EMA2S,":[28],"an":[29],"end-to-end":[30],"multimodal":[31,49,63],"articulatory-to-speech":[32],"system":[33,70,95],"that":[34,61,84],"directly":[35],"converts":[36],"to":[39],"signals.":[41],"We":[42],"a":[44],"neural-network-based":[45],"vocoder":[46],"combined":[47],"joint-training,":[50],"incorporating":[51],"spectrogram,":[52],"mel-spectrogram,":[53],"and":[54,77,87],"deep":[55,88],"features.":[56],"The":[57],"experimental":[58],"results":[59,82],"confirm":[60],"the":[62,68],"approach":[64],"of":[65,73],"EMA2S":[66],"outperforms":[67],"baseline":[69],"terms":[72],"both":[74],"objective":[75],"evaluation":[76,79],"subjective":[78],"metrics.":[80],"Moreover,":[81],"demonstrate":[83],"joint":[85],"mel-spectrogram":[86],"feature":[89],"loss":[90],"training":[91],"effectively":[93],"improve":[94],"performance.":[96]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
