{"id":"https://openalex.org/W2788444423","doi":"https://doi.org/10.1109/icassp.2018.8461596","title":"Visual-Only Recognition of Normal, Whispered and Silent Speech","display_name":"Visual-Only Recognition of Normal, Whispered and Silent Speech","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2788444423","doi":"https://doi.org/10.1109/icassp.2018.8461596","mag":"2788444423"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1802.06399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Dept. of Computing, Imperial College London, London, UK","Department of Computing, Imperial College London, London, UK ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK (","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101405147","display_name":"Jie Shen","orcid":"https://orcid.org/0000-0002-6722-2754"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Shen","raw_affiliation_strings":["Dept. of Computing, Imperial College London, London, UK","Department of Computing, Imperial College London, London, UK ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK (","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022973340","display_name":"Doruk Cetin","orcid":"https://orcid.org/0009-0002-7319-6940"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Doruk Cetin","raw_affiliation_strings":["Dept. of Computing, Imperial College London, London, UK","Department of Computing, Imperial College London, London, UK ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK (","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Dept. of Computing, Imperial College London, London, UK","Department of Computing, Imperial College London, London, UK ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK (","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.1804,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.30126972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6219","last_page":"6223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8154450058937073},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.6909791231155396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6903884410858154},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.650973379611969},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5455216765403748},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.45270344614982605},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.41348040103912354},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3760170042514801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2504153549671173},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.16198813915252686}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8154450058937073},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.6909791231155396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6903884410858154},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.650973379611969},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5455216765403748},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.45270344614982605},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.41348040103912354},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3760170042514801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2504153549671173},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.16198813915252686},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2018.8461596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1802.06399","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06399","pdf_url":"https://arxiv.org/pdf/1802.06399","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,"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":"","raw_type":"text"},{"id":"mag:2788444423","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1802.06399.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,"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:spiral.imperial.ac.uk:10044/1/73204","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/73204","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"Conference Paper"},{"id":"doi:10.48550/arxiv.1802.06399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.06399","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,"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1802.06399","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06399","pdf_url":"https://arxiv.org/pdf/1802.06399","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,"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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2788444423.pdf","grobid_xml":"https://content.openalex.org/works/W2788444423.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W65758255","https://openalex.org/W107924225","https://openalex.org/W1522301498","https://openalex.org/W2008120082","https://openalex.org/W2041470347","https://openalex.org/W2087681821","https://openalex.org/W2096391593","https://openalex.org/W2100495367","https://openalex.org/W2230777371","https://openalex.org/W2396724490","https://openalex.org/W2404704342","https://openalex.org/W2578229578","https://openalex.org/W2580471497","https://openalex.org/W2952746495","https://openalex.org/W2963192365","https://openalex.org/W2963528589","https://openalex.org/W6631564540","https://openalex.org/W6631943919","https://openalex.org/W6632013873","https://openalex.org/W6660882451","https://openalex.org/W6704242068","https://openalex.org/W6712664211","https://openalex.org/W6734790163","https://openalex.org/W6743738265","https://openalex.org/W6765296696"],"related_works":["https://openalex.org/W2962915147","https://openalex.org/W2246823171","https://openalex.org/W2796771987","https://openalex.org/W3102538494","https://openalex.org/W2608946313","https://openalex.org/W2403418871","https://openalex.org/W2802623045","https://openalex.org/W2803550782","https://openalex.org/W2577857724","https://openalex.org/W1556750318","https://openalex.org/W1597082751","https://openalex.org/W36394764","https://openalex.org/W1970155899","https://openalex.org/W2344609090","https://openalex.org/W2800753652","https://openalex.org/W2737982026","https://openalex.org/W3184757502","https://openalex.org/W2163680580","https://openalex.org/W188308949","https://openalex.org/W2983423850"],"abstract_inverted_index":{"Silent":[0],"speech":[1,27,67,107,170,188],"interfaces":[2],"have":[3,42],"been":[4,43],"recently":[5,39],"proposed":[6,40],"as":[7],"a":[8,74,186],"way":[9],"to":[10,24,125,147,184],"enable":[11],"communication":[12],"when":[13,129,151],"the":[14,22,38,56,66,90,97,102,105,110,152,168,173],"acoustic":[15],"signal":[16],"is":[17,50,79,96,127,149],"not":[18,192],"available.":[19],"This":[20,49,159],"introduces":[21],"need":[23],"build":[25],"visual":[26,111,165],"recognition":[28,189],"systems":[29,41],"for":[30],"silent":[31,87,157,187],"and":[32,82,86,131,135,138,172],"whispered":[33,85],"speech.":[34,88,158],"However,":[35],"almost":[36],"all":[37],"trained":[44],"on":[45,65,133,156],"vocalised":[46],"data":[47,179],"only.":[48,113],"in":[51,55,120],"contrast":[52],"with":[53],"evidence":[54],"literature":[57],"which":[58,78,100],"suggests":[59],"that":[60,116,161,176],"lip":[61],"movements":[62],"change":[63],"depending":[64],"mode.":[68],"In":[69],"this":[70,95],"work,":[71],"we":[72],"introduce":[73],"new":[75],"audiovisual":[76],"database":[77],"publicly":[80],"available":[81],"contains":[83],"normal,":[84],"To":[89],"best":[91],"of":[92,123,145],"our":[93],"knowledge,":[94],"first":[98],"study":[99],"investigates":[101],"differences":[103,166],"between":[104,167],"three":[106],"modes":[108,171],"using":[109],"modality":[112],"We":[114],"show":[115],"an":[117],"absolute":[118],"decrease":[119,144],"classification":[121],"rate":[122],"up":[124,146],"3.7%":[126],"observed":[128],"training":[130,178],"testing":[132],"normal":[134],"whispered,":[136],"respectively,":[137],"vice":[139],"versa.":[140],"An":[141],"even":[142],"higher":[143],"8.5%":[148],"reported":[150],"models":[153],"are":[154,163],"tested":[155],"reveals":[160],"there":[162],"indeed":[164],"3":[169],"common":[174],"assumption":[175],"vocalized":[177],"can":[180],"be":[181,193],"used":[182],"directly":[183],"train":[185],"system":[190],"may":[191],"true.":[194]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}