{"id":"https://openalex.org/W2892611740","doi":"https://doi.org/10.1109/slt.2018.8639643","title":"Audio-Visual Speech Recognition with a Hybrid CTC/Attention Architecture","display_name":"Audio-Visual Speech Recognition with a Hybrid CTC/Attention Architecture","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2892611740","doi":"https://doi.org/10.1109/slt.2018.8639643","mag":"2892611740"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.00108","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Samsung AI Center, Cambridge, UK","Department of Computing Imperial College London UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center, Cambridge, UK","institution_ids":["https://openalex.org/I4210117523"]},{"raw_affiliation_string":"Department of Computing Imperial College London UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["Computer Vision Laboratory, University of Nottingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, University of Nottingham, UK","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001790767","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0003-3752-0803"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["Dept. of Computing, Imperial College London, UK","Department of Computing Imperial College London UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing Imperial College London UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024224610","display_name":"Georgios Tzimiropoulos","orcid":"https://orcid.org/0000-0002-1803-5338"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgios Tzimiropoulos","raw_affiliation_strings":["Computer Vision Laboratory, University of Nottingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, University of Nottingham, UK","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Samsung AI Center, Cambridge, UK","Department of Computing Imperial College London UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center, Cambridge, UK","institution_ids":["https://openalex.org/I4210117523"]},{"raw_affiliation_string":"Department of Computing Imperial College London UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4988,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.6457668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"513","last_page":"520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9977999925613403,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.793036937713623},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7542014122009277},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.648527204990387},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5569790005683899},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5238357186317444},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.49910545349121094},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.49273255467414856},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4900256395339966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43960943818092346},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43810662627220154},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.43597468733787537},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39425745606422424},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32102707028388977},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.2736737132072449},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25037437677383423},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1887933909893036},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07122689485549927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793036937713623},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7542014122009277},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.648527204990387},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5569790005683899},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5238357186317444},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.49910545349121094},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.49273255467414856},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4900256395339966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43960943818092346},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43810662627220154},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.43597468733787537},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39425745606422424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32102707028388977},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2736737132072449},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25037437677383423},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1887933909893036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07122689485549927},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt.2018.8639643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.00108","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.00108","pdf_url":"https://arxiv.org/pdf/1810.00108","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2892611740","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1810.00108","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/73211","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/73211","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Workshop on Spoken Language Technology (SLT)","raw_type":"Conference Paper"},{"id":"doi:10.48550/arxiv.1810.00108","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1810.00108","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.00108","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.00108","pdf_url":"https://arxiv.org/pdf/1810.00108","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5015807494","display_name":"TalkingHeads: Audiovisual Speech Recognition in-the-wild","funder_award_id":"706668","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2892611740.pdf","grobid_xml":"https://content.openalex.org/works/W2892611740.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1503933356","https://openalex.org/W1974387177","https://openalex.org/W2096391593","https://openalex.org/W2121486117","https://openalex.org/W2267805933","https://openalex.org/W2404704342","https://openalex.org/W2474638510","https://openalex.org/W2516412152","https://openalex.org/W2551572271","https://openalex.org/W2766219058","https://openalex.org/W2962780374","https://openalex.org/W2963030892","https://openalex.org/W2963192365","https://openalex.org/W2963295405","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W4245919820","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6631564540","https://openalex.org/W6686207219","https://openalex.org/W6692642783","https://openalex.org/W6713551954","https://openalex.org/W6729540071","https://openalex.org/W6734491695","https://openalex.org/W6746574493","https://openalex.org/W6753038255","https://openalex.org/W6754079011","https://openalex.org/W6754392867","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W2963785710","https://openalex.org/W3161697668","https://openalex.org/W2526425061","https://openalex.org/W2752238778","https://openalex.org/W2968682061","https://openalex.org/W2982640351","https://openalex.org/W2613107983","https://openalex.org/W2890197052","https://openalex.org/W2905699315","https://openalex.org/W3199490845","https://openalex.org/W2132423630","https://openalex.org/W3096339849","https://openalex.org/W142758689","https://openalex.org/W2889624961","https://openalex.org/W3202709306","https://openalex.org/W2964182350","https://openalex.org/W3143539582","https://openalex.org/W2892009249","https://openalex.org/W3035299099","https://openalex.org/W2725379595"],"abstract_inverted_index":{"Recent":[0],"works":[1],"in":[2,39,45,122,160],"speech":[3,78],"recognition":[4,76,101],"rely":[5],"either":[6],"on":[7,136],"connectionist":[8],"temporal":[9],"classification":[10],"(CTC)":[11],"or":[12],"sequence-to-sequence":[13],"models":[14,27],"for":[15,74,99,164],"character-level":[16],"recognition.":[17],"CTC":[18,37],"assumes":[19],"conditional":[20,60],"independence":[21,61],"of":[22,58,77,83,102,168],"individual":[23],"characters,":[24],"whereas":[25],"attention-based":[26,43],"can":[28],"provide":[29],"nonsequential":[30],"alignments.":[31],"Therefore,":[32],"we":[33,66],"could":[34],"use":[35,67,105],"a":[36,93],"loss":[38],"combination":[40],"with":[41],"an":[42,118],"model":[44,115,129,149,154],"order":[46],"to":[47,117,156],"force":[48],"monotonic":[49],"alignments":[50],"and":[51,109,130],"at":[52],"the":[53,59,68,81,88,106,112,127,132,147,152,171],"same":[54],"time":[55,90],"get":[56],"rid":[57],"assumption.":[62],"In":[63],"this":[64,86],"paper,":[65],"recently":[69],"proposed":[70,113],"hybrid":[71,94],"CTC/attention":[72],"architecture":[73,95,96],"audio-visual":[75,100,114,148],"in-the-wild.":[79],"To":[80],"best":[82],"our":[84],"knowledge,":[85],"is":[87,97],"first":[89],"that":[91,111,146],"such":[92],"used":[98],"speech.":[103],"We":[104,143],"LRS2":[107,137],"database":[108,138],"show":[110],"leads":[116],"1.3%":[119],"absolute":[120,158],"decrease":[121],"word":[123,140,161],"error":[124,141,162],"rate":[125],"over":[126],"audio-only":[128],"achieves":[131],"new":[133],"state-of-the-art":[134],"performance":[135],"(7%":[139],"rate).":[142],"also":[144],"observe":[145],"significantly":[150],"outperforms":[151],"audio-based":[153],"(up":[155],"32.9%":[157],"improvement":[159],"rate)":[163],"several":[165],"different":[166],"types":[167],"noise":[169],"as":[170],"signal-to-noise":[172],"ratio":[173],"decreases.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2025-10-10T00:00:00"}