{"id":"https://openalex.org/W2108140737","doi":"https://doi.org/10.1109/isspa.2005.1580196","title":"Distinctive feature fusion for improved audio-visual phoneme recognition","display_name":"Distinctive feature fusion for improved audio-visual phoneme recognition","publication_year":2006,"publication_date":"2006-10-04","ids":{"openalex":"https://openalex.org/W2108140737","doi":"https://doi.org/10.1109/isspa.2005.1580196","mag":"2108140737"},"language":"en","primary_location":{"id":"doi:10.1109/isspa.2005.1580196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2005.1580196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5059991648","display_name":"Trent Lewis","orcid":"https://orcid.org/0000-0002-4025-4019"},"institutions":[{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"T.W. Lewis","raw_affiliation_strings":["School of Informatics and Engineering, Flinders University, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Engineering, Flinders University, Adelaide, Australia","institution_ids":["https://openalex.org/I169541294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085737719","display_name":"David Powers","orcid":"https://orcid.org/0000-0001-5998-2262"},"institutions":[{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"D.M.W. Powers","raw_affiliation_strings":["School of Informatics and Engineering, Flinders University, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Engineering, Flinders University, Adelaide, Australia","institution_ids":["https://openalex.org/I169541294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I169541294"],"apc_list":null,"apc_paid":null,"fwci":0.6316,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6197278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"62","last_page":"65"},"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":0.9990000128746033,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9951000213623047,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7936428189277649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7920136451721191},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6919066905975342},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6633084416389465},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6142235994338989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6037819385528564},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5759509205818176},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48270583152770996},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.43983617424964905},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43982207775115967},{"id":"https://openalex.org/keywords/distinctive-feature","display_name":"Distinctive feature","score":0.4247549772262573},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12563127279281616},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.07629534602165222},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0662727952003479}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7936428189277649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7920136451721191},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6919066905975342},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6633084416389465},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6142235994338989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6037819385528564},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5759509205818176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48270583152770996},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.43983617424964905},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43982207775115967},{"id":"https://openalex.org/C2778744346","wikidata":"https://www.wikidata.org/wiki/Q1152224","display_name":"Distinctive feature","level":2,"score":0.4247549772262573},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12563127279281616},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.07629534602165222},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0662727952003479},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isspa.2005.1580196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2005.1580196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.flinders.edu.au:2328/14400","is_oa":false,"landing_page_url":"http://hdl.handle.net/2328/14400","pdf_url":null,"source":{"id":"https://openalex.org/S4306401120","display_name":"Flinders Academic Commons (Flinders University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169541294","host_organization_name":"Flinders University","host_organization_lineage":["https://openalex.org/I169541294"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W161516627","https://openalex.org/W177229737","https://openalex.org/W1505981264","https://openalex.org/W1527928020","https://openalex.org/W1589328436","https://openalex.org/W1590447358","https://openalex.org/W1970533835","https://openalex.org/W2010800472","https://openalex.org/W2013699441","https://openalex.org/W2042165210","https://openalex.org/W2096391593","https://openalex.org/W2101630471","https://openalex.org/W2118333821","https://openalex.org/W2125943500","https://openalex.org/W2134723767","https://openalex.org/W4231869218","https://openalex.org/W4256399001","https://openalex.org/W6606494575","https://openalex.org/W6607211750","https://openalex.org/W6631539414","https://openalex.org/W6678697574"],"related_works":["https://openalex.org/W2283145973","https://openalex.org/W340537008","https://openalex.org/W2030239325","https://openalex.org/W162020606","https://openalex.org/W2038007203","https://openalex.org/W2067569460","https://openalex.org/W1969662601","https://openalex.org/W2039725445","https://openalex.org/W2380120374","https://openalex.org/W73806164"],"abstract_inverted_index":{"Auditory":[0],"and":[1,37],"visual":[2],"signals":[3],"provide":[4],"complementary":[5],"information":[6,55],"but":[7],"few":[8],"applications":[9],"successfully":[10],"combine":[11],"the":[12,41,46,48,57,65],"two":[13],"sources.":[14],"We":[15],"consider":[16],"a":[17],"distinctive":[18,85],"feature":[19,86],"approach":[20,50],"to":[21,32],"Audio":[22],"Visual":[23],"Automatic":[24],"Speech":[25],"Recognition":[26],"(AV-ASR)":[27],"in":[28,40],"which":[29],"features":[30],"appropriate":[31],"each":[33,76],"modality":[34,59],"are":[35],"employed,":[36],"demonstrate":[38],"that":[39],"absence":[42],"of":[43],"knowledge":[44],"about":[45],"noise":[47],"modality-specific":[49],"is":[51,70,80],"best.":[52],"However":[53],"even":[54],"from":[56,88],"non-preferred":[58],"can":[60],"be":[61],"usefully":[62],"employed":[63],"if":[64],"environmental":[66],"context":[67],"(e.g.":[68],"SNR)":[69],"accounted":[71],"for":[72],"by":[73,95],"adaptively":[74],"weighting":[75],"modality.":[77],"Future":[78],"research":[79],"focusing":[81],"on":[82],"deriving":[83],"these":[84],"automatically":[87],"data":[89],"rather":[90],"than":[91],"using":[92],"those":[93],"proposed":[94],"linguists.":[96]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2016-06-24T00:00:00"}
