{"id":"https://openalex.org/W3192265757","doi":null,"title":"Voice Reconstruction from Silent Speech with a Sequence-to-Sequence Model","display_name":"Voice Reconstruction from Silent Speech with a Sequence-to-Sequence Model","publication_year":2021,"publication_date":"2021-07-31","ids":{"openalex":"https://openalex.org/W3192265757","mag":"3192265757"},"language":"en","primary_location":{"id":"mag:3192265757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2108.00190.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.00190.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100355355","display_name":"Huiyan Li","orcid":"https://orcid.org/0000-0002-2700-8550","observed_orcids":["https://orcid.org/0000-0002-2700-8550"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huiyan Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2700-8550","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102482811","display_name":"Haohong Lin","orcid":"https://orcid.org/0009-0006-3786-3557","observed_orcids":["https://orcid.org/0009-0006-3786-3557"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haohong Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430226","display_name":"You Wang","orcid":"https://orcid.org/0000-0003-2766-1581","observed_orcids":["https://orcid.org/0000-0003-2766-1581"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2766-1581","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027266566","display_name":"Hengyang Wang","orcid":"https://orcid.org/0000-0002-6054-243X","observed_orcids":["https://orcid.org/0000-0002-6054-243X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hengyang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030078778","display_name":"Han Gao","orcid":"https://orcid.org/0000-0002-2947-7764","observed_orcids":["https://orcid.org/0000-0002-2947-7764"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Gao","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2947-7764","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qing Ai","orcid":"https://orcid.org/0000-0002-8081-6805","observed_orcids":["https://orcid.org/0000-0002-8081-6805"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Ai","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8081-6805","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100765203","display_name":"Guang Li","orcid":"https://orcid.org/0000-0002-0698-6822","observed_orcids":["https://orcid.org/0000-0002-0698-6822"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guang Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0698-6822","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.4860999882221222,"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":0.4860999882221222,"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":0.4794999957084656,"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/T10863","display_name":"Voice and Speech Disorders","score":0.015200000256299973,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/surface-electromyography","display_name":"surface electromyography","score":0.9049999713897705},{"id":"https://openalex.org/keywords/voice-restoration","display_name":"voice restoration","score":0.6800000071525574},{"id":"https://openalex.org/keywords/sequence-to-sequence-models","display_name":"sequence-to-sequence models","score":0.9169999957084656},{"id":"https://openalex.org/keywords/phoneme-classification","display_name":"phoneme classification","score":0.8849999904632568},{"id":"https://openalex.org/keywords/mandarin-speech","display_name":"Mandarin speech","score":0.6850000023841858}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7978925704956055},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7138890027999878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6673416495323181},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.518223762512207},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4864649474620819},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.45714879035949707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33073627948760986},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11461380124092102},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10631775856018066},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3192265757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2108.00190.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3192265757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2108.00190.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W116902681","https://openalex.org/W128773739","https://openalex.org/W169623250","https://openalex.org/W180745309","https://openalex.org/W329375248","https://openalex.org/W1488659701","https://openalex.org/W1506507878","https://openalex.org/W1663785051","https://openalex.org/W1963623761","https://openalex.org/W1967225830","https://openalex.org/W1982352919","https://openalex.org/W1988581148","https://openalex.org/W2000439420","https://openalex.org/W2001496424","https://openalex.org/W2008120082","https://openalex.org/W2017586035","https://openalex.org/W2025341678","https://openalex.org/W2039640471","https://openalex.org/W2049363352","https://openalex.org/W2053777938","https://openalex.org/W2067295501","https://openalex.org/W2107860279","https://openalex.org/W2118849696","https://openalex.org/W2126143605","https://openalex.org/W2128989405","https://openalex.org/W2145442746","https://openalex.org/W2160594205","https://openalex.org/W2168918709","https://openalex.org/W2284628133","https://openalex.org/W2419247625","https://openalex.org/W2519091744","https://openalex.org/W2540507509","https://openalex.org/W2626778328","https://openalex.org/W2747874407","https://openalex.org/W2761532371","https://openalex.org/W2768153200","https://openalex.org/W2769402512","https://openalex.org/W2806172474","https://openalex.org/W2898847420","https://openalex.org/W2913994460","https://openalex.org/W2914048585","https://openalex.org/W2952609044","https://openalex.org/W2962780374","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2984862052","https://openalex.org/W2992647453","https://openalex.org/W3010627145","https://openalex.org/W3013691153","https://openalex.org/W3013952251","https://openalex.org/W3015338123","https://openalex.org/W3033411150","https://openalex.org/W3035083561","https://openalex.org/W3040975780","https://openalex.org/W3083438180","https://openalex.org/W3094002217","https://openalex.org/W3096567388","https://openalex.org/W3098304089","https://openalex.org/W3105229878","https://openalex.org/W3137160941","https://openalex.org/W3162517041","https://openalex.org/W3175752069"],"related_works":["https://openalex.org/W4283383330","https://openalex.org/W4417402977","https://openalex.org/W4308348295","https://openalex.org/W3166461476","https://openalex.org/W7130386958","https://openalex.org/W3105229878","https://openalex.org/W4417337364","https://openalex.org/W7072222899","https://openalex.org/W4313001800","https://openalex.org/W2144849627"],"abstract_inverted_index":{"Silent":[0],"Speech":[1],"Decoding":[2],"(SSD)":[3],"based":[4],"on":[5,98],"Surface":[6],"electromyography":[7],"(sEMG)":[8],"has":[9],"become":[10],"a":[11,99],"prevalent":[12],"task":[13],"in":[14],"recent":[15],"years.":[16],"Though":[17],"revolutions":[18],"have":[19],"been":[20],"proposed":[21,113],"to":[22,25,42,57,73,91],"decode":[23],"sEMG":[24,52,77,88],"audio":[26,79],"successfully,":[27],"some":[28],"problems":[29],"still":[30],"remain.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,62,82],"propose":[36],"an":[37],"optimized":[38],"sequence-to-sequence":[39],"(Seq2Seq)":[40],"approach":[41],"synthesize":[43],"voice":[44,120],"from":[45,65],"subvocal":[46,49,69,76],"sEMG.":[47],"Both":[48],"and":[50,55,70,86,119],"vocal":[51,71,87],"are":[53],"collected":[54],"preprocessed":[56],"provide":[58],"data":[59],"information.":[60],"Then,":[61],"extract":[63],"durations":[64],"the":[66,75,93,112,116],"alignment":[67],"between":[68],"signals":[72],"regulate":[74],"following":[78],"length.":[80],"Besides,":[81],"use":[83],"phoneme":[84],"classification":[85],"reconstruction":[89],"modules":[90],"improve":[92],"model":[94,114],"performance.":[95],"Finally,":[96],"experiments":[97],"Mandarin":[100],"speaker":[101],"dataset,":[102],"which":[103],"consists":[104],"of":[105,108,122],"6.49":[106],"hours":[107],"data,":[109],"demonstrate":[110],"that":[111],"improves":[115],"mapping":[117],"accuracy":[118],"quality":[121],"reconstructed":[123],"voice.":[124]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-08-16T00:00:00"}