{"id":"https://openalex.org/W3095933030","doi":"https://doi.org/10.21437/interspeech.2020-3003","title":"Resource-Adaptive Deep Learning for Visual Speech Recognition","display_name":"Resource-Adaptive Deep Learning for Visual Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095933030","doi":"https://doi.org/10.21437/interspeech.2020-3003","mag":"3095933030"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-3003","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","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/A5055069331","display_name":"Alexandros Koumparoulis","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alexandros Koumparoulis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079262240","display_name":"Edmilson Morais","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edmilson da Silva Morais","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055069331"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7619,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71805274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3510","last_page":"3514"},"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/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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7642639875411987},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5759795904159546},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5091590285301208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45014503598213196},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4468402564525604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642639875411987},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5759795904159546},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5091590285301208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45014503598213196},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4468402564525604},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-3003","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:ir.lib.uth.gr:11615/75307","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/75307","pdf_url":null,"source":{"id":"https://openalex.org/S4306400243","display_name":"University of Thessaly Institutional Repository (University of Thessaly)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145722265","host_organization_name":"University of Thessaly","host_organization_lineage":["https://openalex.org/I145722265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH","raw_type":"conferenceItem"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1998294030","https://openalex.org/W2029199293","https://openalex.org/W2194775991","https://openalex.org/W2578229578","https://openalex.org/W2612445135","https://openalex.org/W2746799361","https://openalex.org/W2767286248","https://openalex.org/W2774812352","https://openalex.org/W2790109708","https://openalex.org/W2804600264","https://openalex.org/W2886564777","https://openalex.org/W2889448058","https://openalex.org/W2889624961","https://openalex.org/W2890952074","https://openalex.org/W2891226622","https://openalex.org/W2935794029","https://openalex.org/W2949117887","https://openalex.org/W2952746495","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W2963420686","https://openalex.org/W2963528589","https://openalex.org/W2964207404","https://openalex.org/W2964308564","https://openalex.org/W2972719006","https://openalex.org/W2990503944","https://openalex.org/W3106250896"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W4323565446"],"abstract_inverted_index":{"We":[0,115],"focus":[1],"on":[2,37,41,99,119,169],"the":[3,72,76,100,104,111,120,170],"problem":[4],"of":[5,89,103,127,134,180],"efficient":[6,31,143],"architectures":[7],"for":[8,15],"lipreading":[9,34,73,126],"that":[10,63],"allow":[11],"trading-off":[12],"computational":[13],"resources":[14],"visual":[16],"speech":[17],"recognition":[18,57],"accuracy.":[19],"In":[20],"particular,":[21],"we":[22,27,53],"make":[23],"two":[24],"contributions:":[25],"First,":[26],"introduce":[28],"MobiLipNetV3,":[29],"an":[30],"and":[32,43,67,151,188],"accurate":[33],"model,":[35,106],"based":[36,149],"our":[38,117],"earlier":[39],"work":[40],"MobiLipNetV2":[42],"incorporating":[44],"recent":[45],"advances":[46],"in":[47,71,124,158,193],"convolutional":[48],"neural":[49,147],"network":[50,148],"architectures.":[51],"Second,":[52],"propose":[54],"a":[55,65,68,80,87,177,183,189],"novel":[56],"paradigm,":[58],"called":[59],"MultiRate":[60],"Ensemble":[61],"(MRE),":[62],"combines":[64],"\u201clean\u201d":[66],"\u201cfull\u201d":[69,105],"MobiLipNetV3":[70],"pipeline,":[74],"with":[75],"latter":[77],"applied":[78],"at":[79],"lower":[81],"frame":[82],"rate.":[83],"This":[84],"architecture":[85],"yields":[86,182],"family":[88,133],"systems":[90,135],"offering":[91],"multiple":[92],"accuracy":[93],"vs.":[94],"efficiency":[95],"operating":[96,173],"points":[97],"depending":[98,168],"frame-rate":[101],"decimation":[102,179],"thus":[107],"allowing":[108],"adaptation":[109],"to":[110,139,145,153,163],"available":[112],"device":[113],"resources.":[114],"evaluate":[116],"approach":[118],"TCD-TIMIT":[121],"corpus,":[122],"popular":[123],"speaker-independent":[125],"continuous":[128],"speech.":[129],"The":[130],"proposed":[131],"MRE":[132,171],"can":[136],"be":[137],"up":[138,152,162],"73":[140],"times":[141],"more":[142],"compared":[144],"residual":[146],"lipreading,":[150],"twice":[154],"as":[155],"MobiLipNetV2,":[156],"while":[157],"both":[159],"cases":[160],"reaching":[161],"8%":[164],"absolute":[165,185],"WER":[166,186],"reduction,":[167],"chosen":[172],"point.":[174],"For":[175],"example,":[176],"temporal":[178],"three":[181],"7%":[184],"reduction":[187],"26%":[190],"relative":[191],"decrease":[192],"computations":[194],"over":[195],"MobiLipNetV2.":[196],"\u00a9":[197],"2020":[198],"ISCA":[199]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-11-09T00:00:00"}