{"id":"https://openalex.org/W2696731410","doi":"https://doi.org/10.1109/icassp.2017.7953172","title":"Improving audio-visual speech recognition using deep neural networks with dynamic stream reliability estimates","display_name":"Improving audio-visual speech recognition using deep neural networks with dynamic stream reliability estimates","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2696731410","doi":"https://doi.org/10.1109/icassp.2017.7953172","mag":"2696731410"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5091137706","display_name":"Hendrik Meutzner","orcid":"https://orcid.org/0000-0002-5403-5642"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hendrik Meutzner","raw_affiliation_strings":["Insititute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Insititute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067036469","display_name":"Ning Ma","orcid":"https://orcid.org/0000-0002-4112-3109"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ning Ma","raw_affiliation_strings":["Insititute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Insititute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075524022","display_name":"Robert M. Nickel","orcid":"https://orcid.org/0009-0005-5007-5355"},"institutions":[{"id":"https://openalex.org/I131221577","display_name":"Bucknell University","ror":"https://ror.org/00fc1qt65","country_code":"US","type":"education","lineage":["https://openalex.org/I131221577"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Nickel","raw_affiliation_strings":["Bucknell University, Lewisburg, PA, USA"],"affiliations":[{"raw_affiliation_string":"Bucknell University, Lewisburg, PA, USA","institution_ids":["https://openalex.org/I131221577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035233948","display_name":"Christopher Schymura","orcid":"https://orcid.org/0000-0002-6128-3556"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christopher Schymura","raw_affiliation_strings":["Insititute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Insititute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007017640","display_name":"Dorothea Kolossa","orcid":"https://orcid.org/0000-0003-0678-3053"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dorothea Kolossa","raw_affiliation_strings":["Insititute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Insititute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091137706"],"corresponding_institution_ids":["https://openalex.org/I904495901"],"apc_list":null,"apc_paid":null,"fwci":3.9175,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9475584,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5320","last_page":"5324"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8290148973464966},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6987656354904175},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6631731986999512},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5324797630310059},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5128979682922363},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4756440818309784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4333909749984741},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43209919333457947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8290148973464966},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6987656354904175},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6631731986999512},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5324797630310059},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5128979682922363},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4756440818309784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4333909749984741},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43209919333457947},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2017.7953172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:121254","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W72757270","https://openalex.org/W1524333225","https://openalex.org/W1969975883","https://openalex.org/W2015143272","https://openalex.org/W2022799064","https://openalex.org/W2024490110","https://openalex.org/W2044222806","https://openalex.org/W2076462394","https://openalex.org/W2101045344","https://openalex.org/W2131342762","https://openalex.org/W2133115605","https://openalex.org/W2136922672","https://openalex.org/W2146324387","https://openalex.org/W2155998647","https://openalex.org/W2161025448","https://openalex.org/W2295119550","https://openalex.org/W2398828702","https://openalex.org/W2406846463","https://openalex.org/W2579335913","https://openalex.org/W6602923018","https://openalex.org/W6631362777","https://openalex.org/W6697090674","https://openalex.org/W6713551954","https://openalex.org/W6732514500"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W1707372784","https://openalex.org/W2096006843"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,44,59,98],"recognition":[2,13,60],"is":[3,111,123,146],"a":[4,29,86,106,150],"promising":[5],"approach":[6,153],"to":[7,73,125,148],"tackling":[8],"the":[9,69,114,137,142,159],"problem":[10],"of":[11,54,71,128,158],"reduced":[12],"rates":[14],"under":[15],"adverse":[16],"acoustic":[17,38,76],"conditions.":[18],"However,":[19,68],"finding":[20],"an":[21],"optimal":[22],"mechanism":[23,145],"for":[24,36],"combining":[25],"multi-modal":[26,129],"information":[27,41,79],"remains":[28],"challenging":[30],"task.":[31],"Various":[32],"methods":[33],"are":[34,103],"applicable":[35],"integrating":[37],"and":[39,77],"visual":[40,78],"in":[42,95],"Gaussian-mixture-model-based":[43],"recognition,":[45],"e.g.,":[46],"via":[47],"dynamic":[48,92,101],"stream":[49,93],"weighting.":[50],"The":[51,100],"recent":[52],"advances":[53],"deep":[55],"neural":[56],"network":[57],"(DNN)-based":[58],"promise":[61],"improved":[62],"performance":[63],"when":[64],"using":[65],"audio-visual":[66,97],"information.":[67],"question":[70],"how":[72],"optimally":[74],"integrate":[75],"remains.":[80],"In":[81],"this":[82,120],"paper,":[83],"we":[84],"propose":[85],"state-based":[87,121],"integration":[88,122,127,134],"scheme":[89],"that":[90,110,119,154],"uses":[91],"weights":[94,102],"DNN-based":[96],"recognition.":[99],"obtained":[104],"from":[105,113],"time-variant":[107],"reliability":[108,139],"estimate":[109],"derived":[112],"audio":[115],"signal.":[116],"We":[117],"show":[118],"superior":[124],"early":[126,133],"features,":[130],"even":[131],"if":[132],"also":[135],"includes":[136],"proposed":[138,143],"estimate.":[140],"Furthermore,":[141],"adaptive":[144],"able":[147],"outperform":[149],"fixed":[151],"weighting":[152],"exploits":[155],"oracle":[156],"knowledge":[157],"true":[160],"signal-to-noise":[161],"ratio.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}