{"id":"https://openalex.org/W2774812352","doi":"https://doi.org/10.1109/taslp.2017.2783545","title":"Comparing Fusion Models for DNN-Based Audiovisual Continuous Speech Recognition","display_name":"Comparing Fusion Models for DNN-Based Audiovisual Continuous Speech Recognition","publication_year":2017,"publication_date":"2017-12-14","ids":{"openalex":"https://openalex.org/W2774812352","doi":"https://doi.org/10.1109/taslp.2017.2783545","mag":"2774812352"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2783545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2783545","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101807751","display_name":"Ahmed Hussen Abdelaziz","orcid":"https://orcid.org/0000-0001-8027-4666"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]},{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ahmed Hussen Abdelaziz","raw_affiliation_strings":["Apple Inc., Cupertino, CA, USA","International Computer Science Institute, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Apple Inc., Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]},{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101807751"],"corresponding_institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I4210153776"],"apc_list":null,"apc_paid":null,"fwci":3.5136,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.940937,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"26","issue":"3","first_page":"475","last_page":"484"},"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":0.9993000030517578,"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":0.9950000047683716,"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":0.843673586845398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8042459487915039},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.796573281288147},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7501325607299805},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5054218769073486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46139904856681824},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4253201186656952},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4131265878677368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843673586845398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8042459487915039},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.796573281288147},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7501325607299805},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5054218769073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46139904856681824},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4253201186656952},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4131265878677368},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2783545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2783545","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1454360699","https://openalex.org/W1503933356","https://openalex.org/W1518556865","https://openalex.org/W1524333225","https://openalex.org/W1576996184","https://openalex.org/W1635512741","https://openalex.org/W1904457459","https://openalex.org/W1922557984","https://openalex.org/W1974387177","https://openalex.org/W1978380426","https://openalex.org/W2002342963","https://openalex.org/W2014621385","https://openalex.org/W2015143272","https://openalex.org/W2017262259","https://openalex.org/W2022330547","https://openalex.org/W2022799064","https://openalex.org/W2024490110","https://openalex.org/W2029199293","https://openalex.org/W2034480015","https://openalex.org/W2038359238","https://openalex.org/W2051091181","https://openalex.org/W2076462394","https://openalex.org/W2091349387","https://openalex.org/W2096391593","https://openalex.org/W2097349831","https://openalex.org/W2101045344","https://openalex.org/W2105833168","https://openalex.org/W2114016253","https://openalex.org/W2118877769","https://openalex.org/W2118977726","https://openalex.org/W2120974626","https://openalex.org/W2121430128","https://openalex.org/W2121486117","https://openalex.org/W2121606987","https://openalex.org/W2130103520","https://openalex.org/W2131342762","https://openalex.org/W2133115605","https://openalex.org/W2139055331","https://openalex.org/W2158069733","https://openalex.org/W2164598857","https://openalex.org/W2165119652","https://openalex.org/W2171330332","https://openalex.org/W2184188583","https://openalex.org/W2289394825","https://openalex.org/W2289925289","https://openalex.org/W2303024254","https://openalex.org/W2398828702","https://openalex.org/W2474638510","https://openalex.org/W2509591453","https://openalex.org/W2519224033","https://openalex.org/W2550980560","https://openalex.org/W2746799361","https://openalex.org/W2747876639","https://openalex.org/W2752520680","https://openalex.org/W2916986993","https://openalex.org/W2952746495","https://openalex.org/W2963192365","https://openalex.org/W2963217176","https://openalex.org/W2987657883","https://openalex.org/W4231869218","https://openalex.org/W4302613066","https://openalex.org/W6631362777","https://openalex.org/W6654645376","https://openalex.org/W6659166873","https://openalex.org/W6677548441","https://openalex.org/W6679388247","https://openalex.org/W6686207219","https://openalex.org/W6712354604","https://openalex.org/W6729540071","https://openalex.org/W6765296696","https://openalex.org/W6845679800"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W3134920593","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2071828724","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256"],"abstract_inverted_index":{"Audiovisual":[0],"fusion":[1,68,78,103,107,111,131],"is":[2,133,171],"one":[3],"of":[4,19,45,100,129,169],"the":[5,17,26,34,43,63,98,105,109,113,119,123,161],"most":[6],"challenging":[7],"tasks":[8],"that":[9,65],"continues":[10],"to":[11,41,160,196,201],"attract":[12],"substantial":[13],"research":[14,74],"interest":[15],"in":[16,49,62,143,174],"field":[18],"audiovisual":[20,77,102,165],"automatic":[21,46],"speech":[22,47,84],"recognition":[23,48,85,173],"(AV-ASR).":[24],"In":[25],"last":[27],"few":[28,57],"decades,":[29],"many":[30],"approaches":[31,208],"for":[32,70,80,193],"integrating":[33],"audio":[35],"and":[36,52,96,122,151,185,188,207],"video":[37],"modalities":[38],"were":[39],"proposed":[40],"enhance":[42],"performance":[44,99],"both":[50],"clean":[51,187],"noisy":[53,189],"conditions.":[54],"However,":[55],"very":[56],"studies":[58],"can":[59,209],"be":[60,197,210],"found":[61],"literature":[64],"compare":[66],"different":[67],"models":[69,79,87,132,206],"AV-ASR.":[71],"Even":[72],"less":[73],"work":[75],"compares":[76,97],"large":[81],"vocabulary":[82],"continuous":[83,175],"(LVCSR)":[86],"using":[88,135],"deep":[89],"neural":[90],"networks":[91],"(DNNs).":[92],"This":[93],"paper":[94],"reviews":[95],"five":[101],"models:":[104],"feature":[106],"model,":[108,112],"decision":[110],"multistream":[114],"hidden":[115],"Markov":[116],"model":[117],"(HMM),":[118],"coupled":[120],"HMM,":[121],"turbo":[124],"decoders.":[125],"A":[126],"complete":[127],"evaluation":[128],"these":[130],"conducted":[134],"a":[136,147,149,152,198],"standard":[137],"speaker-independent":[138],"DNN-based":[139],"LVCSR":[140,204],"Kaldi":[141],"recipe":[142],"three":[144],"experimental":[145],"setups:":[146],"clean-train-clean-test,":[148],"clean-train-noisy-test,":[150],"matched-training":[153],"setup.":[154],"All":[155],"experiments":[156],"have":[157],"been":[158],"applied":[159],"recently":[162],"released":[163],"NTCD-TIMIT":[164,170,178],"corpus.":[166],"The":[167],"task":[168],"phone":[172],"speech.":[176],"Using":[177],"with":[179],"its":[180],"freely":[181],"available":[182],"visual":[183],"features":[184],"37":[186],"acoustic":[190],"signals":[191],"allows":[192],"this":[194],"study":[195],"common":[199],"benchmark,":[200],"which":[202],"novel":[203],"AV-ASR":[205],"compared.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
