{"id":"https://openalex.org/W4415433908","doi":"https://doi.org/10.21437/interspeech.2025-565","title":"Articulatory Feature Prediction from Surface EMG during Speech Production","display_name":"Articulatory Feature Prediction from Surface EMG during Speech Production","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433908","doi":"https://doi.org/10.21437/interspeech.2025-565"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-565","doi":"https://doi.org/10.21437/interspeech.2025-565","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-565","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.13814","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100674127","display_name":"Jihwan Lee","orcid":"https://orcid.org/0000-0001-9380-5470","observed_orcids":["https://orcid.org/0000-0001-9380-5470","https://orcid.org/0009-0009-3033-2042"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jihwan Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kevin Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048302987","display_name":"Kleanthis Avramidis","orcid":"https://orcid.org/0000-0003-0308-795X","observed_orcids":["https://orcid.org/0000-0003-0308-795X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kleanthis Avramidis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118790284","display_name":"Simon Pistrosch","orcid":"https://orcid.org/0009-0002-6763-7981","observed_orcids":["https://orcid.org/0009-0002-6763-7981"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Pistrosch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092639611","display_name":"Monica Gonzalez-Machorro","orcid":"https://orcid.org/0009-0008-9188-058X","observed_orcids":["https://orcid.org/0009-0008-9188-058X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Monica Gonzalez-Machorro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053205419","display_name":"Yoonjeong Lee","orcid":"https://orcid.org/0000-0003-1323-049X","observed_orcids":["https://orcid.org/0000-0003-1323-049X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoonjeong Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn Wolfgang Schuller","orcid":"https://orcid.org/0000-0002-6478-8699","observed_orcids":["https://orcid.org/0000-0002-6478-8699"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110122617","display_name":"Louis M. Goldstein","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Louis Goldstein","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103555640","display_name":"Shrikanth S. Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204","observed_orcids":["https://orcid.org/0000-0002-1052-6204"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.192,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9915545,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"320","last_page":"324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.396699994802475,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology (medical)"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.396699994802475,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology (medical)"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.32519999146461487,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.22190000116825104,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/surface-electromyography","display_name":"surface electromyography","score":0.9779999852180481},{"id":"https://openalex.org/keywords/speech-production","display_name":"speech production","score":0.9869999885559082},{"id":"https://openalex.org/keywords/speech-motor-control","display_name":"speech motor control","score":0.6029999852180481},{"id":"https://openalex.org/keywords/articulation","display_name":"articulation","score":0.5989999771118164}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6040999889373779},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5734000205993652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5318999886512756},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.510200023651123},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4480000138282776},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-565","doi":"https://doi.org/10.21437/interspeech.2025-565","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-565","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.13814","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13814","pdf_url":"https://arxiv.org/pdf/2505.13814","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.13814","doi":"https://doi.org/10.48550/arxiv.2505.13814","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.13814","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.13814","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13814","pdf_url":"https://arxiv.org/pdf/2505.13814","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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4816118824","display_name":"RI Core: Medium: Structured variability in vocal tract articulation dynamics in speech","funder_award_id":"2311676","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5245076518","display_name":"CompCog: Deep causal inference grounds the perception of cognitive objects in speech","funder_award_id":"2240349","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433908.pdf","grobid_xml":"https://content.openalex.org/works/W4415433908.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2160594205","https://openalex.org/W7155174756","https://openalex.org/W1592981438","https://openalex.org/W3097407310","https://openalex.org/W2163551658","https://openalex.org/W7102431148","https://openalex.org/W7098889025","https://openalex.org/W3166461476","https://openalex.org/W4411593749","https://openalex.org/W2144849627"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,23,36,81],"model":[3,18],"for":[4,30,43,104],"predicting":[5],"articulatory":[6,31,45,53,78,98],"features":[7,54],"from":[8,74],"surface":[9,75],"electromyography":[10],"(EMG)":[11],"signals":[12],"during":[13],"speech":[14,60,72,86,114],"production.":[15],"The":[16,109],"proposed":[17],"integrates":[19],"convolutional":[20],"layers":[21],"and":[22,97,112],"Transformer":[24],"block,":[25],"followed":[26],"by":[27],"separate":[28],"predictors":[29],"features.":[32,46],"Our":[33],"approach":[34,83],"achieves":[35],"high":[37],"prediction":[38],"correlation":[39],"of":[40],"approximately":[41],"0.9":[42],"most":[44],"Furthermore,":[47],"we":[48,89],"demonstrate":[49],"that":[50],"these":[51],"predicted":[52],"can":[55],"be":[56],"decoded":[57,113],"into":[58],"intelligible":[59],"waveforms.":[61],"To":[62],"our":[63],"knowledge,":[64],"this":[65],"is":[66],"the":[67,91],"first":[68],"method":[69],"to":[70,84],"decode":[71],"waveforms":[73],"EMG":[76,94,106],"via":[77],"features,":[79],"offering":[80],"novel":[82],"EMG-based":[85],"synthesis.":[87],"Additionally,":[88],"analyze":[90],"relationship":[92],"between":[93],"electrode":[95,107],"placement":[96],"feature":[99],"predictability,":[100],"providing":[101],"knowledge-driven":[102],"insights":[103],"optimizing":[105],"configurations.":[108],"source":[110],"code":[111],"samples":[115],"are":[116],"publicly":[117],"available.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2025-10-24T00:00:00"}
