{"id":"https://openalex.org/W4385823397","doi":"https://doi.org/10.21437/interspeech.2023-1966","title":"Silent Speech Recognition with Articulator Positions Estimated from Tongue Ultrasound and Lip Video","display_name":"Silent Speech Recognition with Articulator Positions Estimated from Tongue Ultrasound and Lip Video","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823397","doi":"https://doi.org/10.21437/interspeech.2023-1966"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1966","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/362207774/INTERSPEECHSubm_Korin_copy_3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092639654","display_name":"Rachel Beeson","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rachel Beeson","raw_affiliation_strings":["University of Edinburgh, Scotland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Scotland","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"institutions":[{"id":"https://openalex.org/I4210159188","display_name":"SpeechTech (Czechia)","ror":"https://ror.org/05fsqes40","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159188"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CZ","GB"],"is_corresponding":false,"raw_author_name":"Korin Richmond","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Scotland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Scotland","institution_ids":["https://openalex.org/I4210159188","https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4833,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58809747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1149","last_page":"1153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9957000017166138,"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/T13289","display_name":"Infant Health and Development","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"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/articulator","display_name":"Articulator","score":0.942821741104126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7504522204399109},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7241915464401245},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.47251826524734497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4580596387386322},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11731097102165222}],"concepts":[{"id":"https://openalex.org/C2778415344","wikidata":"https://www.wikidata.org/wiki/Q443216","display_name":"Articulator","level":2,"score":0.942821741104126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7504522204399109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7241915464401245},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.47251826524734497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580596387386322},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11731097102165222},{"id":"https://openalex.org/C29694066","wikidata":"https://www.wikidata.org/wiki/Q118301","display_name":"Orthodontics","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2023-1966","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f3122927-cf21-4c8c-9efd-31c13b49b81e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/362207774/INTERSPEECHSubm_Korin_copy_3.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Beeson, R & Richmond, K 2023, Silent speech recognition with articulator positions estimated from tongue ultrasound and lip video. in N Harte, J Carson-Berndsen & G Jones (eds), Proceedings of the Annual Conference of the International Speech Communication Association : Interspeech 2023. Interspeech - Annual Conference of the International Speech Communication Association, Dublin, pp. 1149-1153, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-1966","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f3122927-cf21-4c8c-9efd-31c13b49b81e","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/f3122927-cf21-4c8c-9efd-31c13b49b81e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/f3122927-cf21-4c8c-9efd-31c13b49b81e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f3122927-cf21-4c8c-9efd-31c13b49b81e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Beeson, R & Richmond, K 2023, Silent speech recognition with articulator positions estimated from tongue ultrasound and lip video. in N Harte, J Carson-Berndsen & G Jones (eds), Proceedings of the Annual Conference of the International Speech Communication Association : Interspeech 2023. Interspeech - Annual Conference of the International Speech Communication Association, Dublin, pp. 1149-1153, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-1966","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/f3122927-cf21-4c8c-9efd-31c13b49b81e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/362207774/INTERSPEECHSubm_Korin_copy_3.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Beeson, R & Richmond, K 2023, Silent speech recognition with articulator positions estimated from tongue ultrasound and lip video. in N Harte, J Carson-Berndsen & G Jones (eds), Proceedings of the Annual Conference of the International Speech Communication Association : Interspeech 2023. Interspeech - Annual Conference of the International Speech Communication Association, Dublin, pp. 1149-1153, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-1966","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W65758255","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1995440941","https://openalex.org/W1995735739","https://openalex.org/W2002342963","https://openalex.org/W2008120082","https://openalex.org/W2028563590","https://openalex.org/W2039640471","https://openalex.org/W2089759944","https://openalex.org/W2295777873","https://openalex.org/W2397670449","https://openalex.org/W2593268422","https://openalex.org/W2756664579","https://openalex.org/W2768153200","https://openalex.org/W2769767375","https://openalex.org/W2887114371","https://openalex.org/W2889418448","https://openalex.org/W2963272864","https://openalex.org/W3096927110","https://openalex.org/W3143787022","https://openalex.org/W3196749493","https://openalex.org/W4210430789","https://openalex.org/W4297797495","https://openalex.org/W4300458848","https://openalex.org/W4388365047"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2034310431","https://openalex.org/W2724655958","https://openalex.org/W2033140727","https://openalex.org/W4250529536","https://openalex.org/W1963633157","https://openalex.org/W4290036070","https://openalex.org/W2412408187","https://openalex.org/W2171350946"],"abstract_inverted_index":{"We":[0,30,50,87],"present":[1,133],"a":[2,19,74],"multi-speaker":[3,20,65,77],"silent":[4,62,101,120],"speech":[5,102,121,136],"recognition":[6,42,99],"system":[7,79],"trained":[8,41,51],"on":[9,58],"articulator":[10,32,115],"features":[11,33,47],"derived":[12],"from":[13],"the":[14,35],"Tongue":[15],"and":[16,26,61,119,122],"Lips":[17],"corpus,":[18],"corpus":[21],"of":[22,84,100],"ultrasound":[23],"tongue":[24],"imaging":[25],"lip":[27],"video":[28],"data.":[29],"extracted":[31],"using":[34,48,103],"pose":[36],"estimation":[37],"software":[38],"DeepLabCut,":[39],"then":[40,55],"models":[43],"with":[44,52],"these":[45],"point-tracking":[46,85],"Kaldi.":[49],"voiced":[53,60,118,135],"utterances,":[54],"tested":[56],"performance":[57],"both":[59],"utterances.":[63],"Our":[64],"SSR":[66,78],"improved":[67],"WER":[68],"by":[69],"23.06%":[70],"when":[71,137],"compared":[72,106],"to":[73,93,107,127],"previous":[75],"similar":[76],"which":[80],"used":[81],"image-based":[82],"instead":[83],"features.":[86,109],"also":[88],"found":[89,123],"great":[90],"improvements":[91],"(up":[92],"15.45%":[94],"decrease":[95],"in":[96,98,114,134],"WER)":[97],"fMLLR":[104],"adaptation":[105],"raw":[108],"Finally,":[110],"we":[111],"investigated":[112],"differences":[113],"trajectories":[116],"between":[117],"that":[124,131],"speakers":[125],"tend":[126],"miss":[128],"articulatory":[129],"targets":[130],"are":[132],"speaking":[138],"silently.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}