{"id":"https://openalex.org/W2022799064","doi":"https://doi.org/10.1109/icassp.2013.6639140","title":"Audio-visual deep learning for noise robust speech recognition","display_name":"Audio-visual deep learning for noise robust speech recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2022799064","doi":"https://doi.org/10.1109/icassp.2013.6639140","mag":"2022799064"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5018240777","display_name":"Jing Huang","orcid":"https://orcid.org/0000-0002-1370-7318"},"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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":185,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7596","last_page":"7599"},"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":0.9997000098228455,"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":0.9977999925613403,"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":0.8012340068817139},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.779537558555603},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.7494571805000305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6614139080047607},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5798856019973755},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5502372980117798},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5379019975662231},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4841064214706421},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.475781112909317},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44225725531578064},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.42186951637268066},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08375266194343567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012340068817139},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.779537558555603},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.7494571805000305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6614139080047607},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5798856019973755},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5502372980117798},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5379019975662231},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4841064214706421},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.475781112909317},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44225725531578064},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.42186951637268066},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08375266194343567}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W39452988","https://openalex.org/W124086577","https://openalex.org/W124185092","https://openalex.org/W1211870555","https://openalex.org/W1506639196","https://openalex.org/W1527928020","https://openalex.org/W1584924955","https://openalex.org/W2002591263","https://openalex.org/W2014621385","https://openalex.org/W2074796660","https://openalex.org/W2096391593","https://openalex.org/W2101630471","https://openalex.org/W2121486117","https://openalex.org/W2121551559","https://openalex.org/W2125610823","https://openalex.org/W2132999255","https://openalex.org/W2133115605","https://openalex.org/W2136922672","https://openalex.org/W2150907703","https://openalex.org/W2153606381","https://openalex.org/W2160815625","https://openalex.org/W2172097686","https://openalex.org/W2184045248","https://openalex.org/W2184188583","https://openalex.org/W2395273492","https://openalex.org/W3099202502","https://openalex.org/W3149335959","https://openalex.org/W4231991966","https://openalex.org/W4235272953","https://openalex.org/W6605059668","https://openalex.org/W6605073824","https://openalex.org/W6627960130","https://openalex.org/W6631539414","https://openalex.org/W6635229022","https://openalex.org/W6686207219","https://openalex.org/W6712039779"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W2150890698","https://openalex.org/W3101844402","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738"],"abstract_inverted_index":{"Deep":[0],"belief":[1],"networks":[2],"(DBN)":[3],"have":[4],"shown":[5],"impressive":[6],"improvements":[7],"over":[8,104],"Gaussian":[9],"mixture":[10],"models":[11],"for":[12,22,37,46],"automatic":[13],"speech":[14,24,40],"recognition.":[15,41],"In":[16],"this":[17],"work":[18],"we":[19,28],"use":[20,29],"DBNs":[21,48],"audio-visual":[23,108],"recognition;":[25],"in":[26,49],"particular,":[27],"deep":[30],"learning":[31],"from":[32,61],"audio":[33],"and":[34,64],"visual":[35],"features":[36,74],"noise":[38],"robust":[39],"We":[42],"test":[43],"two":[44],"methods":[45,92],"using":[47],"a":[50,53,65,81,105],"multimodal":[51],"setting:":[52],"conventional":[54],"decision":[55],"fusion":[56,68],"method":[57,69],"that":[58,70,90],"combines":[59],"scores":[60],"single-modality":[62,78],"DBNs,":[63],"novel":[66],"feature":[67],"operates":[71],"on":[72],"mid-level":[73],"learned":[75],"by":[76,98],"the":[77],"DBNs.":[79],"On":[80],"continuously":[82],"spoken":[83],"digit":[84],"recognition":[85],"task,":[86],"our":[87],"experiments":[88],"show":[89],"these":[91],"can":[93],"reduce":[94],"word":[95],"error":[96],"rate":[97],"as":[99,101],"much":[100],"21%":[102],"relative":[103],"baseline":[106],"multi-stream":[107],"GMM/HMM":[109],"system.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}