{"id":"https://openalex.org/W3135435917","doi":"https://doi.org/10.21437/interspeech.2021-23","title":"Silent versus Modal Multi-Speaker Speech Recognition from Ultrasound and Video","display_name":"Silent versus Modal Multi-Speaker Speech Recognition from Ultrasound and Video","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3135435917","doi":"https://doi.org/10.21437/interspeech.2021-23","mag":"3135435917"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-23","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-23","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.00333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109494794","display_name":"Manuel Sam Ribeiro","orcid":"https://orcid.org/0000-0001-8096-2231"},"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":true,"raw_author_name":"Manuel Sam Ribeiro","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049305990","display_name":"Aciel Eshky","orcid":"https://orcid.org/0000-0002-7746-3412"},"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":"Aciel Eshky","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"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":"Korin Richmond","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"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":"Steve Renals","raw_affiliation_strings":["University of Edinburgh,"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109494794"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.3078,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51325414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9933000206947327,"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/speech-recognition","display_name":"Speech recognition","score":0.7991012334823608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6796599626541138},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6494650840759277},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.49543964862823486},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.44186869263648987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3290855288505554}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7991012334823608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796599626541138},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6494650840759277},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.49543964862823486},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44186869263648987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3290855288505554},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-23","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-23","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.00333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.00333","pdf_url":"https://arxiv.org/pdf/2103.00333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"mag:3135435917","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.00333.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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},{"id":"pmh:oai:pure.ed.ac.uk:openaire/0ae9e7f2-59a8-423f-bb3d-b08e83ce4668","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/0ae9e7f2-59a8-423f-bb3d-b08e83ce4668","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ribeiro, M S, Eshky, A, Richmond, K & Renals, S 2021, Silent versus modal multi-speaker speech recognition from ultrasound and video. in 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech Communication Association, pp. 641-645, Interspeech 2021, Brno, Czech Republic, 30/08/21. https://doi.org/10.21437/Interspeech.2021-23","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.2103.00333","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.00333","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.00333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.00333","pdf_url":"https://arxiv.org/pdf/2103.00333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G7869365812","display_name":null,"funder_award_id":"EP/P02338X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W65758255","https://openalex.org/W107924225","https://openalex.org/W341711312","https://openalex.org/W1524333225","https://openalex.org/W1987337335","https://openalex.org/W1995440941","https://openalex.org/W1995735739","https://openalex.org/W2008120082","https://openalex.org/W2106006415","https://openalex.org/W2295119550","https://openalex.org/W2295777873","https://openalex.org/W2296719434","https://openalex.org/W2397670449","https://openalex.org/W2402146185","https://openalex.org/W2525632221","https://openalex.org/W2593268422","https://openalex.org/W2603597171","https://openalex.org/W2768153200","https://openalex.org/W2769767375","https://openalex.org/W2802863253","https://openalex.org/W2889418448","https://openalex.org/W2935803161","https://openalex.org/W2939800755","https://openalex.org/W2941048526","https://openalex.org/W2963272864","https://openalex.org/W3095897738","https://openalex.org/W3096686028","https://openalex.org/W3096927110","https://openalex.org/W3143787022","https://openalex.org/W3174954176"],"related_works":["https://openalex.org/W3196749493","https://openalex.org/W1799795868","https://openalex.org/W2102152293","https://openalex.org/W2068056889","https://openalex.org/W2020439803","https://openalex.org/W2127019176","https://openalex.org/W1970585285","https://openalex.org/W2143793021","https://openalex.org/W812778724","https://openalex.org/W1004616342","https://openalex.org/W2352540147","https://openalex.org/W2082898764","https://openalex.org/W2263270774","https://openalex.org/W3016246676","https://openalex.org/W297015806","https://openalex.org/W2135870591","https://openalex.org/W2043482182","https://openalex.org/W2134687645","https://openalex.org/W1605605950","https://openalex.org/W2621806538"],"abstract_inverted_index":{"We":[0,17,41,66,86],"investigate":[1],"multi-speaker":[2],"speech":[3,45,54,69,95,134,145,174],"recognition":[4,46,70],"from":[5,24,47,122,173],"ultrasound":[6,123],"images":[7,13],"of":[8,14,33,91,98,104,118,132,139],"the":[9,15,76,89,102,105,110,115,130],"tongue":[10,119,124],"and":[11,27,38,64,82,93,101,142],"video":[12],"lips.":[16],"train":[18],"our":[19],"systems":[20],"on":[21,29],"imaging":[22,48],"data":[23,49],"modal":[25,39,53,94,140,152],"speech,":[26,141],"evaluate":[28],"matched":[30],"test":[31],"sets":[32],"two":[34,156],"speaking":[35,162],"modes:":[36],"silent":[37,44,68,92,133,144],"speech.":[40,153],"observe":[42,128],"that":[43,74,129,138,143],"underperforms":[50],"compared":[51],"to":[52,58],"recognition,":[55],"likely":[56],"due":[57],"a":[59,147],"speaking-mode":[60],"mismatch":[61],"between":[62],"training":[63],"testing.":[65],"improve":[67],"performance":[71],"using":[72],"techniques":[73],"address":[75],"domain":[77],"mismatch,":[78],"such":[79],"as":[80],"fMLLR":[81],"unsupervised":[83],"model":[84],"adaptation.":[85],"also":[87],"analyse":[88],"properties":[90,157],"in":[96],"terms":[97],"utterance":[99],"duration":[100,131],"size":[103],"articulatory":[106,111,149],"space.":[107],"To":[108],"estimate":[109],"space,":[112],"we":[113,127],"compute":[114],"convex":[116],"hull":[117],"splines,":[120],"extracted":[121],"images.":[125],"Overall,":[126],"is":[135],"longer":[136],"than":[137,151],"covers":[146],"smaller":[148],"space":[150],"Although":[154],"these":[155],"are":[158],"statistically":[159],"significant":[160],"across":[161],"modes,":[163],"they":[164],"do":[165],"not":[166],"directly":[167],"correlate":[168],"with":[169],"word":[170],"error":[171],"rates":[172],"recognition.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
