{"id":"https://openalex.org/W2163365749","doi":"https://doi.org/10.21437/icslp.1996-383","title":"Using the visual component in automatic speech recognition","display_name":"Using the visual component in automatic speech recognition","publication_year":1996,"publication_date":"1996-10-03","ids":{"openalex":"https://openalex.org/W2163365749","doi":"https://doi.org/10.21437/icslp.1996-383","mag":"2163365749"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1996-383","doi":"https://doi.org/10.21437/icslp.1996-383","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1996-383","pdf_url":null,"source":{"id":"https://openalex.org/S4363607739","display_name":"International Conference on Spoken Language Processing (ICSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"4th International Conference on Spoken Language Processing (ICSLP 1996)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113323230","display_name":"N. Michael Brooke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"N.M. Brooke","raw_affiliation_strings":["Media Technology Research Centre, School of Mathematical Sciences, University of Bath, Bath, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Technology Research Centre, School of Mathematical Sciences, University of Bath, Bath, UK","institution_ids":["https://openalex.org/I51601045"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5113323230"],"corresponding_institution_ids":["https://openalex.org/I51601045"],"apc_list":null,"apc_paid":null,"fwci":1.1926,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.69081501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":"3","issue":null,"first_page":"1656","last_page":"1659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.961899995803833,"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":0.961899995803833,"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":0.034699998795986176,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0005000000237487257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-speech-recognition","display_name":"visual speech recognition","score":0.6830000281333923},{"id":"https://openalex.org/keywords/facial-gestures","display_name":"facial gestures","score":0.5830000042915344},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.6389999985694885},{"id":"https://openalex.org/keywords/image-compression","display_name":"image compression","score":0.5789999961853027},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"principal component analysis","score":0.7229999899864197},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.9229999780654907},{"id":"https://openalex.org/keywords/audiovisual-integration","display_name":"audiovisual integration","score":0.7409999966621399},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.8640000224113464},{"id":"https://openalex.org/keywords/multimodal-speech-recognition","display_name":"multimodal speech recognition","score":0.6060000061988831},{"id":"https://openalex.org/keywords/hearing-loss","display_name":"hearing loss","score":0.5490000247955322},{"id":"https://openalex.org/keywords/noise","display_name":"noise","score":0.4869999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036917448043823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7225193381309509},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6006194353103638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5398001670837402},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5269114375114441},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5131760239601135},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.46717390418052673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43866729736328125},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.4327840805053711},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.422691285610199},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3222222328186035},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/icslp.1996-383","doi":"https://doi.org/10.21437/icslp.1996-383","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1996-383","pdf_url":null,"source":{"id":"https://openalex.org/S4363607739","display_name":"International Conference on Spoken Language Processing (ICSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"4th International Conference on Spoken Language Processing (ICSLP 1996)","raw_type":"proceedings-article"},{"id":"doi:10.1109/icslp.1996.607943","doi":"https://doi.org/10.1109/icslp.1996.607943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icslp.1996.607943","pdf_url":null,"source":{"id":"https://openalex.org/S4363607739","display_name":"International Conference on Spoken Language Processing (ICSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.16.4309","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.16.4309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.asel.udel.edu/icslp/cdrom/vol3/999/a999.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W588265","https://openalex.org/W22517275","https://openalex.org/W177229737","https://openalex.org/W432563302","https://openalex.org/W991614603","https://openalex.org/W1523010034","https://openalex.org/W1529401398","https://openalex.org/W1929733467","https://openalex.org/W1934584000","https://openalex.org/W1964178275","https://openalex.org/W1988089926","https://openalex.org/W1994530392","https://openalex.org/W2002621203","https://openalex.org/W2115116459","https://openalex.org/W2124174353","https://openalex.org/W2328570161","https://openalex.org/W2487271655","https://openalex.org/W4394607900","https://openalex.org/W4394624217","https://openalex.org/W4396560814","https://openalex.org/W4399805489","https://openalex.org/W6864505273","https://openalex.org/W6864705362","https://openalex.org/W6866052491","https://openalex.org/W6869632044"],"related_works":["https://openalex.org/W2167271218","https://openalex.org/W1991959239","https://openalex.org/W2171917108","https://openalex.org/W7096608296","https://openalex.org/W2060598099","https://openalex.org/W2115116459","https://openalex.org/W171560785","https://openalex.org/W2001508456","https://openalex.org/W2055997173","https://openalex.org/W124086577"],"abstract_inverted_index":{"The":[0],"movements":[1],"of":[2,43,48,54,92,106,121],"talkers'":[3,49],"faces":[4,50],"are":[5],"known":[6],"to":[7,33],"convey":[8],"visual":[9,96],"cues":[10],"that":[11,26,99],"can":[12,68,103],"improve":[13],"speech":[14,35],"intelligibility,":[15],"especially":[16],"where":[17],"there":[18],"is":[19,89],"noise":[20],"or":[21,81],"hearing":[22],"impairment.":[23],"This":[24],"suggests":[25],"visible":[27],"facial":[28],"gestures":[29],"could":[30],"be":[31,69,104],"exploited":[32],"enhance":[34],"intelligibility":[36],"in":[37],"automatic":[38],"systems.":[39],"Handling":[40],"the":[41,90,93,100,107],"volume":[42],"data":[44,55,97],"represented":[45],"by":[46],"images":[47],"implies":[51],"some":[52],"form":[53],"compression.":[56],"Rather":[57],"than":[58],"using":[59,71],"conventional":[60],"feature":[61],"extraction":[62],"approaches,":[63],"image":[64],"coding":[65],"and":[66,95],"compression":[67],"achieved":[70],"data-driven,":[72],"statistically-oriented":[73],"techniques":[74],"such":[75],"as":[76],"artificial":[77],"neural":[78],"networks":[79],"(ANNs)":[80],"principal":[82],"component":[83],"analysis":[84],"(PCA).":[85],"A":[86],"major":[87],"issue":[88],"combination":[91],"audio":[94],"so":[98],"best":[101],"use":[102,124],"made":[105],"two":[108],"modalities":[109],"together.":[110],"Perceptual":[111],"experiments":[112],"may":[113],"offer":[114],"guidance":[115],"on":[116],"suitable":[117],"machine":[118],"architectures,":[119],"many":[120],"which":[122],"currently":[123],"hidden":[125],"Markov":[126],"models":[127],"(HMMs).":[128]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}