{"id":"https://openalex.org/W4372264243","doi":"https://doi.org/10.1109/icassp49357.2023.10097120","title":"Multi-Speaker Speech Synthesis from Electromyographic Signals by Soft Speech Unit Prediction","display_name":"Multi-Speaker Speech Synthesis from Electromyographic Signals by Soft Speech Unit Prediction","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372264243","doi":"https://doi.org/10.1109/icassp49357.2023.10097120"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097120","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/A5041361992","display_name":"Kevin Scheck","orcid":null},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Kevin Scheck","raw_affiliation_strings":["University of Bremen,Cognitive Systems Lab,Bremen,Germany"],"affiliations":[{"raw_affiliation_string":"University of Bremen,Cognitive Systems Lab,Bremen,Germany","institution_ids":["https://openalex.org/I180437899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tanja Schultz","raw_affiliation_strings":["University of Bremen,Cognitive Systems Lab,Bremen,Germany"],"affiliations":[{"raw_affiliation_string":"University of Bremen,Cognitive Systems Lab,Bremen,Germany","institution_ids":["https://openalex.org/I180437899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041361992"],"corresponding_institution_ids":["https://openalex.org/I180437899"],"apc_list":null,"apc_paid":null,"fwci":3.2604,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93007825,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"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":0.9987000226974487,"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":0.9987000226974487,"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":0.9979000091552734,"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":0.9962999820709229,"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/speech-recognition","display_name":"Speech recognition","score":0.818305253982544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7230931520462036},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6599692702293396},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.63286292552948},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6116809844970703},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.5910929441452026},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4779220223426819},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4513801336288452},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4393460750579834},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.42333370447158813},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34924596548080444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2438412606716156}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.818305253982544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230931520462036},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6599692702293396},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.63286292552948},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6116809844970703},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.5910929441452026},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4779220223426819},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4513801336288452},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4393460750579834},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.42333370447158813},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34924596548080444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2438412606716156},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097120","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":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W169623250","https://openalex.org/W1846051119","https://openalex.org/W1932968309","https://openalex.org/W2008120082","https://openalex.org/W2160594205","https://openalex.org/W2395817516","https://openalex.org/W2419247625","https://openalex.org/W2537327199","https://openalex.org/W2745644908","https://openalex.org/W2768153200","https://openalex.org/W2945478979","https://openalex.org/W2998572311","https://openalex.org/W3024869864","https://openalex.org/W3092028330","https://openalex.org/W3105229878","https://openalex.org/W3140429000","https://openalex.org/W3161695192","https://openalex.org/W3175752069","https://openalex.org/W3197659778","https://openalex.org/W3197763626","https://openalex.org/W3197912330","https://openalex.org/W3210530853","https://openalex.org/W4224926225","https://openalex.org/W4283383330","https://openalex.org/W4286747238","https://openalex.org/W4291824895","https://openalex.org/W4311000453","https://openalex.org/W6762533536","https://openalex.org/W6772349387","https://openalex.org/W6783867762","https://openalex.org/W6847363464","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W3115948027","https://openalex.org/W2405110677","https://openalex.org/W1654407288","https://openalex.org/W4387323809","https://openalex.org/W1977838979","https://openalex.org/W2334129531","https://openalex.org/W2515097069","https://openalex.org/W2738829087","https://openalex.org/W2164829670","https://openalex.org/W4300049944"],"abstract_inverted_index":{"Electromyographic":[0],"(EMG)":[1],"signals":[2],"of":[3,115,117,128],"articulatory":[4],"muscles":[5],"reflect":[6],"the":[7,13,20,42,101,107,126],"speech":[8,39,69,73,86,91,130],"production":[9],"process":[10],"even":[11],"if":[12],"user":[14],"is":[15,46,58,110],"speaking":[16],"silently":[17],"i.e.":[18],"moving":[19],"articulators":[21],"without":[22],"producing":[23],"audible":[24],"sound.":[25],"We":[26],"propose":[27],"Speech-Unit-based":[28],"EMG-to-Speech":[29],"(SU-E2S),":[30],"a":[31,61,76],"system":[32,65],"which":[33,40,66],"relies":[34],"on":[35,60,111],"EMG":[36,94],"to":[37,100],"synthesize":[38],"contains":[41],"articulated":[43],"content":[44],"but":[45,124],"vocalized":[47],"in":[48,113,131],"another":[49],"voice,":[50],"determined":[51],"by":[52,88],"an":[53],"acoustic":[54,68,82,119],"reference":[55],"utterance.":[56],"It":[57],"based":[59],"Voice":[62],"Conversion":[63],"(VC)":[64],"decomposes":[67],"into":[70],"continuous":[71],"soft":[72,90],"units":[74,92],"and":[75,79,95],"speaker":[77],"embedding":[78],"then":[80],"reconstructs":[81],"features.":[83],"SU-E2S":[84,108],"performs":[85],"synthesis":[87],"predicting":[89,118],"from":[93,122],"using":[96],"them":[97],"as":[98],"input":[99],"VC":[102],"system.":[103],"Experiments":[104],"show":[105],"that":[106],"output":[109],"par":[112],"terms":[114],"intelligibility":[116],"features":[120],"directly":[121],"EMG,":[123],"adds":[125],"functionality":[127],"synthesizing":[129],"other":[132],"voices.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}