{"id":"https://openalex.org/W2406799669","doi":"https://doi.org/10.1109/icassp.2016.7472187","title":"Robust audiovisual speech recognition using noise-adaptive linear discriminant analysis","display_name":"Robust audiovisual speech recognition using noise-adaptive linear discriminant analysis","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2406799669","doi":"https://doi.org/10.1109/icassp.2016.7472187","mag":"2406799669"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5046724251","display_name":"Steffen Zeiler","orcid":"https://orcid.org/0009-0002-9594-2633"},"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":"Steffen Zeiler","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/A5032789606","display_name":"Robert Nicheli","orcid":null},"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 Nicheli","raw_affiliation_strings":["Bucknell University, Lewisburg, PA, US"],"affiliations":[{"raw_affiliation_string":"Bucknell University, Lewisburg, PA, US","institution_ids":["https://openalex.org/I131221577"]}]},{"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/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ning Ma","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080527909","display_name":"Guy J. Brown","orcid":"https://orcid.org/0000-0001-8565-5476"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guy J. Brown","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"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":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046724251"],"corresponding_institution_ids":["https://openalex.org/I904495901"],"apc_list":null,"apc_paid":null,"fwci":3.3094,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92960796,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9994999766349792,"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":0.9966999888420105,"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":0.7973573207855225},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7963653206825256},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.754887580871582},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7519696950912476},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6060725450515747},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5151296854019165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46667587757110596},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46522945165634155},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.41760221123695374},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4101375937461853},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08095061779022217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973573207855225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7963653206825256},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.754887580871582},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7519696950912476},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6060725450515747},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5151296854019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46667587757110596},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46522945165634155},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.41760221123695374},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4101375937461853},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08095061779022217},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:102623","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W258638584","https://openalex.org/W1495679096","https://openalex.org/W1536024295","https://openalex.org/W1576996184","https://openalex.org/W1578856370","https://openalex.org/W1610379133","https://openalex.org/W1634594820","https://openalex.org/W1689583599","https://openalex.org/W1960653181","https://openalex.org/W1969975883","https://openalex.org/W1973283204","https://openalex.org/W1978380426","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2017262259","https://openalex.org/W2024490110","https://openalex.org/W2070707809","https://openalex.org/W2083329939","https://openalex.org/W2105833168","https://openalex.org/W2121606987","https://openalex.org/W2129031807","https://openalex.org/W2138377320","https://openalex.org/W2141769559","https://openalex.org/W2142075667","https://openalex.org/W2145475542","https://openalex.org/W2146324387","https://openalex.org/W2147502806","https://openalex.org/W2159094433","https://openalex.org/W2406954482","https://openalex.org/W2407156959","https://openalex.org/W2494535400","https://openalex.org/W2987657883","https://openalex.org/W3099202502","https://openalex.org/W3152750074","https://openalex.org/W4245919820","https://openalex.org/W4285719527","https://openalex.org/W6609694752","https://openalex.org/W6641135991","https://openalex.org/W6642905459","https://openalex.org/W6713510121","https://openalex.org/W6713873095","https://openalex.org/W6723787966","https://openalex.org/W6785273600"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2150890698","https://openalex.org/W2401394187","https://openalex.org/W4245698648","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W66535911","https://openalex.org/W2118882708"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2,82,120],"(ASR)":[3],"has":[4],"become":[5],"a":[6],"widespread":[7],"and":[8,66,76,79,116,129],"convenient":[9],"mode":[10],"of":[11,97],"human-machine":[12],"interaction,":[13],"but":[14],"it":[15],"is":[16,36,42],"still":[17,90],"not":[18],"sufficiently":[19],"reliable":[20],"when":[21],"used":[22],"under":[23],"highly":[24],"noisy":[25],"or":[26],"reverberant":[27],"conditions.":[28],"One":[29],"option":[30],"for":[31,56,71,108,125],"achieving":[32],"far":[33],"greater":[34],"robustness":[35],"to":[37],"include":[38],"another":[39],"modality":[40],"that":[41,118],"unaffected":[43],"by":[44],"acoustic":[45],"noise,":[46],"such":[47,57],"as":[48],"video":[49,77],"information.":[50],"Currently":[51],"the":[52,95,114],"most":[53],"successful":[54],"approaches":[55],"audiovisual":[58],"ASR":[59],"systems,":[60],"coupled":[61,127],"hidden":[62],"Markov":[63],"models":[64],"(HMMs)":[65],"turbo":[67,130],"decoding,":[68],"both":[69,88,126],"allow":[70],"slight":[72],"asynchrony":[73],"between":[74],"audio":[75,98],"features,":[78,99],"significantly":[80],"improve":[81],"rates":[83],"in":[84,94],"this":[85],"way.":[86],"However,":[87],"typically":[89],"neglect":[91],"residual":[92],"errors":[93],"estimation":[96],"so-called":[100],"observation":[101,111],"uncertainties.":[102],"This":[103],"paper":[104],"compares":[105],"two":[106],"strategies":[107],"adding":[109],"these":[110],"uncertainties":[112],"into":[113],"decoder,":[115],"shows":[117],"significant":[119],"rate":[121],"improvements":[122],"are":[123],"achievable":[124],"HMMs":[128],"decoding.":[131]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}