{"id":"https://openalex.org/W4392904696","doi":"https://doi.org/10.1109/icassp48485.2024.10448428","title":"LITEVSR: Efficient Visual Speech Recognition by Learning from Speech Representations of Unlabeled Data","display_name":"LITEVSR: Efficient Visual Speech Recognition by Learning from Speech Representations of Unlabeled Data","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904696","doi":"https://doi.org/10.1109/icassp48485.2024.10448428"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5039305053","display_name":"Hendrik Laux","orcid":"https://orcid.org/0000-0002-0671-4149"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hendrik Laux","raw_affiliation_strings":["University Hospital RWTH Aachen,Germany","University Hospital RWTH Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Hospital RWTH Aachen,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"University Hospital RWTH Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030647112","display_name":"Emil Mededovic","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emil Mededovic","raw_affiliation_strings":["University Hospital RWTH Aachen,Germany","University Hospital RWTH Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Hospital RWTH Aachen,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"University Hospital RWTH Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003503441","display_name":"Ahmed Hallawa","orcid":"https://orcid.org/0000-0003-3932-4873"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ahmed Hallawa","raw_affiliation_strings":["Clinomic Medical GmbH,Aachen,Germany","Clinomic Medical GmbH, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clinomic Medical GmbH,Aachen,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Clinomic Medical GmbH, Aachen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020505546","display_name":"Lukas M\u00e4rtin","orcid":"https://orcid.org/0000-0001-8650-5090"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Martin","raw_affiliation_strings":["Clinomic Medical GmbH,Aachen,Germany","Clinomic Medical GmbH, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clinomic Medical GmbH,Aachen,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Clinomic Medical GmbH, Aachen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057966799","display_name":"Arne Peine","orcid":"https://orcid.org/0000-0003-4163-2402"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arne Peine","raw_affiliation_strings":["Clinomic Medical GmbH,Aachen,Germany","Clinomic Medical GmbH, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clinomic Medical GmbH,Aachen,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Clinomic Medical GmbH, Aachen, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072895220","display_name":"Anke Schmeink","orcid":"https://orcid.org/0000-0002-9929-2925"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anke Schmeink","raw_affiliation_strings":["RWTH Aachen University,Chair of Information Theory and Data Analytics,Germany","Chair of Information Theory and Data Analytics, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair of Information Theory and Data Analytics,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Chair of Information Theory and Data Analytics, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10391","last_page":"10395"},"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":0.9995999932289124,"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":0.9991999864578247,"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":0.797001302242279},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.727210283279419},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6717795133590698},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5915202498435974},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5252689123153687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4510875344276428},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4404565691947937},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4106734097003937},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34997543692588806},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3452572226524353},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3328087329864502},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.25605297088623047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.797001302242279},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.727210283279419},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6717795133590698},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5915202498435974},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5252689123153687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4510875344276428},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4404565691947937},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4106734097003937},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34997543692588806},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3452572226524353},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3328087329864502},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25605297088623047},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1527102103","https://openalex.org/W2015143272","https://openalex.org/W2115252128","https://openalex.org/W2127141656","https://openalex.org/W2194775991","https://openalex.org/W2551572271","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2893436174","https://openalex.org/W2962784628","https://openalex.org/W2963785710","https://openalex.org/W2972756321","https://openalex.org/W2974231335","https://openalex.org/W2981501041","https://openalex.org/W3006974783","https://openalex.org/W3015830103","https://openalex.org/W3035042697","https://openalex.org/W3035682985","https://openalex.org/W3097777922","https://openalex.org/W3162293946","https://openalex.org/W3197140813","https://openalex.org/W3197567540","https://openalex.org/W3199527474","https://openalex.org/W4221153068","https://openalex.org/W4289665794","https://openalex.org/W4293363567","https://openalex.org/W4298112588","https://openalex.org/W4307286264","https://openalex.org/W4317039283","https://openalex.org/W4385245566","https://openalex.org/W4386076364","https://openalex.org/W6677618333","https://openalex.org/W6732872814","https://openalex.org/W6745245109","https://openalex.org/W6754420807","https://openalex.org/W6767671539","https://openalex.org/W6810168380","https://openalex.org/W6847902775"],"related_works":["https://openalex.org/W2944691285","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W151018310","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W2008737763","https://openalex.org/W4385611764"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,39,65,107,112,127],"novel,":[4],"resource-efficient":[5,133],"approach":[6],"to":[7,95],"Visual":[8],"Speech":[9,20],"Recognition":[10,21],"(VSR)":[11],"leveraging":[12],"speech":[13],"representations":[14],"produced":[15],"by":[16],"any":[17],"trained":[18,40,105],"Automatic":[19],"(ASR)":[22],"model.":[23],"Moving":[24],"away":[25],"from":[26,38],"the":[27,75,84,90],"resource-intensive":[28],"trends":[29],"prevalent":[30],"in":[31],"recent":[32],"literature,":[33],"our":[34,61],"method":[35],"distills":[36],"knowledge":[37],"Conformer-based":[41],"ASR":[42],"model,":[43],"achieving":[44],"competitive":[45],"performance":[46],"on":[47,74,106,123],"standard":[48],"VSR":[49,122,134],"benchmarks":[50],"with":[51,86],"significantly":[52],"less":[53],"resource":[54],"utilization.":[55],"Using":[56],"unlabeled":[57],"audio-visual":[58],"data":[59],"only,":[60],"baseline":[62],"model":[63,85,102],"achieves":[64],"word":[66,91],"error":[67,92],"rate":[68,93],"(WER)":[69],"of":[70,118],"47.4%":[71],"and":[72,77,98,115,132],"54.7%":[73],"LRS2":[76],"LRS3":[78],"test":[79],"benchmarks,":[80],"respectively.":[81],"After":[82],"fine-tuning":[83],"limited":[87],"labeled":[88],"data,":[89],"reduces":[94],"35%":[96],"(LRS2)":[97],"45.7%":[99],"(LRS3).":[100],"Our":[101],"can":[103],"be":[104],"single":[108],"consumer-grade":[109],"GPU":[110],"within":[111],"few":[113],"days":[114],"is":[116],"capable":[117],"performing":[119],"real-time":[120],"end-to-end":[121],"dated":[124],"hardware,":[125],"suggesting":[126],"path":[128],"towards":[129],"more":[130],"accessible":[131],"methodologies.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
