{"id":"https://openalex.org/W4205996202","doi":"https://doi.org/10.23919/eusipco54536.2021.9616215","title":"Resource-efficient TDNN Architectures for Audio-visual Speech Recognition","display_name":"Resource-efficient TDNN Architectures for Audio-visual Speech Recognition","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4205996202","doi":"https://doi.org/10.23919/eusipco54536.2021.9616215"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616215","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616215","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 29th European Signal Processing Conference (EUSIPCO)","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":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Alexandros Koumparoulis","raw_affiliation_strings":["ECE Dept., Univ. of Thessaly, Volos, Greece"],"affiliations":[{"raw_affiliation_string":"ECE Dept., Univ. of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["ECE Dept., Univ. of Thessaly, Volos, Greece"],"affiliations":[{"raw_affiliation_string":"ECE Dept., Univ. of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI,Yorktown Heights,USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI,Yorktown Heights,USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079262240","display_name":"Edmilson Morais","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113516","display_name":"IBM Research - Brazil","ror":"https://ror.org/01fxqdx25","country_code":"BR","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113516","https://openalex.org/I4210114115"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Edmilson da Silva Morais","raw_affiliation_strings":["IBM Research AI,S\u00e3o Paulo,Brazil"],"affiliations":[{"raw_affiliation_string":"IBM Research AI,S\u00e3o Paulo,Brazil","institution_ids":["https://openalex.org/I4210113516"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055069331"],"corresponding_institution_ids":["https://openalex.org/I145722265"],"apc_list":null,"apc_paid":null,"fwci":0.1721,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.41520861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"506","last_page":"510"},"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/T11309","display_name":"Music and Audio Processing","score":0.9937000274658203,"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":0.9894000291824341,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8212692737579346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7838788032531738},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6623227000236511},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6187587976455688},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5957314372062683},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.544446587562561},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5273091793060303},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4717738628387451},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4589676856994629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45596760511398315},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43979552388191223},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4332680404186249},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41952648758888245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212692737579346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7838788032531738},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6623227000236511},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6187587976455688},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5957314372062683},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.544446587562561},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5273091793060303},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4717738628387451},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4589676856994629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45596760511398315},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43979552388191223},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4332680404186249},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41952648758888245},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":2,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616215","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616215","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:ir.lib.uth.gr:11615/75305","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/75305","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":"European Signal Processing Conference","raw_type":"conferenceItem"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W587794757","https://openalex.org/W1524333225","https://openalex.org/W1836465849","https://openalex.org/W1998294030","https://openalex.org/W2029199293","https://openalex.org/W2117671523","https://openalex.org/W2551572271","https://openalex.org/W2612754342","https://openalex.org/W2747876639","https://openalex.org/W2790109708","https://openalex.org/W2790326622","https://openalex.org/W2888867175","https://openalex.org/W2889624961","https://openalex.org/W2890952074","https://openalex.org/W2901907199","https://openalex.org/W2935794029","https://openalex.org/W2952218014","https://openalex.org/W2963125010","https://openalex.org/W2963295405","https://openalex.org/W2963370694","https://openalex.org/W2963654155","https://openalex.org/W2963785710","https://openalex.org/W2972630480","https://openalex.org/W2972719006","https://openalex.org/W2973085229","https://openalex.org/W3006974783","https://openalex.org/W3011234510","https://openalex.org/W3011877917","https://openalex.org/W3015281123","https://openalex.org/W3015383493","https://openalex.org/W3015537910","https://openalex.org/W3015966793","https://openalex.org/W3095933030","https://openalex.org/W3096104971","https://openalex.org/W3099330747","https://openalex.org/W3102469722","https://openalex.org/W3106250896","https://openalex.org/W3106423890","https://openalex.org/W3157685993","https://openalex.org/W3162707322","https://openalex.org/W3163211337","https://openalex.org/W4295092762","https://openalex.org/W4297775537","https://openalex.org/W6617368339","https://openalex.org/W6631362777","https://openalex.org/W6638667902","https://openalex.org/W6737664043","https://openalex.org/W6754392867","https://openalex.org/W6777479377","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2262333520","https://openalex.org/W3102785448","https://openalex.org/W2573596907","https://openalex.org/W3188427489","https://openalex.org/W1524112065","https://openalex.org/W642007152","https://openalex.org/W3133616812","https://openalex.org/W2108636611","https://openalex.org/W3081952170","https://openalex.org/W2401827384"],"abstract_inverted_index":{"In":[0,57],"this":[1],"paper,":[2],"we":[3,17,53,60],"consider":[4],"the":[5,37,42,62,67,76,87,90,111],"problem":[6],"of":[7,41,93],"resource-efficient":[8,47],"architectures":[9],"for":[10,29,55],"audio-visual":[11],"automatic":[12],"speech":[13,31,103],"recognition":[14,104,145],"(AVSR).":[15],"Specifically,":[16],"complement":[18],"our":[19,94,108],"earlier":[20,95],"work":[21,96],"that":[22,52],"introduced":[23],"efficient":[24,91,130,139],"convolutional":[25],"neural":[26,49],"networks":[27],"(CNNs)":[28],"visual-only":[30],"recognition,":[32],"by":[33],"focusing":[34],"here":[35],"on":[36,86,110],"sequence":[38],"modeling":[39],"component":[40],"architecture,":[43],"proposing":[44],"a":[45,132],"novel":[46],"time-delay":[48],"network":[50],"(TDNN)":[51],"extend":[54],"AVSR.":[56],"more":[58,129,138],"detail,":[59],"introduce":[61],"sTDNN-F":[63,122],"module,":[64],"which":[65],"combines":[66],"factored":[68],"TDNN":[69,134],"(TDNN-F)":[70],"with":[71],"grouped":[72],"fully-connected":[73],"layers":[74],"and":[75,97,102,136,147,150],"shuffle":[77],"operation.":[78],"We":[79,106],"then":[80],"develop":[81],"an":[82],"AVSR":[83,124],"system":[84,125],"based":[85,123],"sTDNN-F,":[88],"incorporating":[89],"CNNs":[92],"other":[98],"standard":[99],"visual":[100],"processing":[101],"modules.":[105],"evaluate":[107],"approach":[109],"popular":[112],"TCD-TIMIT":[113],"corpus,":[114],"under":[115],"two":[116],"speaker-independent":[117],"training/testing":[118],"scenarios.":[119],"Our":[120],"best":[121],"turns":[126],"out":[127],"74%":[128],"than":[131,140],"traditional":[133],"one":[135],"35%":[137],"TDNN-F,":[141],"while":[142],"maintaining":[143],"similar":[144],"accuracy":[146],"noise":[148],"robustness,":[149],"also":[151],"significantly":[152],"outperforming":[153],"its":[154],"audio-only":[155],"counterpart.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-01-25T00:00:00"}