{"id":"https://openalex.org/W73873779","doi":"https://doi.org/10.21437/interspeech.2011-596","title":"Can audio-visual speech recognition outperform acoustically enhanced speech recognition in automotive environment?","display_name":"Can audio-visual speech recognition outperform acoustically enhanced speech recognition in automotive environment?","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W73873779","doi":"https://doi.org/10.21437/interspeech.2011-596","mag":"73873779"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-596","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5085576560","display_name":"Rajitha Navarathna","orcid":"https://orcid.org/0000-0002-0105-4911"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Rajitha Navarathna","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010339637","display_name":"Tristan Kleinschmidt","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tristan Kleinschmidt","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000014182","display_name":"David Dean","orcid":"https://orcid.org/0000-0003-1274-9775"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Dean","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032604032","display_name":"Patrick Lucey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Lucey","raw_affiliation_strings":["Disney Research Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Disney Research Pittsburgh, USA","institution_ids":["https://openalex.org/I4210142140"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085576560"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":0.6125,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6323774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2241","last_page":"2244"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8340824842453003},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8072071075439453},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5284250378608704},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.48240840435028076},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4555974006652832},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4287067949771881},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4199303984642029},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41849660873413086},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.41250288486480713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.375987708568573},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12198853492736816}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8340824842453003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072071075439453},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5284250378608704},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.48240840435028076},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4555974006652832},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4287067949771881},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4199303984642029},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41849660873413086},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.41250288486480713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.375987708568573},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12198853492736816},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-596","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W56075855","https://openalex.org/W142803501","https://openalex.org/W142945732","https://openalex.org/W1578856370","https://openalex.org/W2051057783","https://openalex.org/W2128653836","https://openalex.org/W2149535104","https://openalex.org/W2165589448"],"related_works":["https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2964829415","https://openalex.org/W1583620810","https://openalex.org/W2341426843","https://openalex.org/W1911859126","https://openalex.org/W2009814707","https://openalex.org/W4387712795"],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2,8,15,67,76,129],"visual":[3,123],"features":[4],"in":[5,26,60,111],"the":[6,13,65,122,126,130],"form":[7],"lip":[9],"movements":[10],"to":[11,22,56],"improve":[12],"performance":[14,113],"acoustic":[16,28,39,102],"speech":[17,35,77,84,103,133],"recognition":[18,36,78,112,134],"has":[19],"been":[20],"shown":[21],"work":[23],"well,":[24],"particularly":[25],"noisy":[27],"conditions.However,":[29],"whether":[30],"this":[31],"technique":[32],"can":[33,94,114],"outperform":[34,95],"incorporating":[37],"well-known":[38],"enhancement":[40,104],"techniques,":[41],"such":[42],"as":[43,98,100],"spectral":[44],"subtraction,":[45],"or":[46],"multi-channel":[47,101],"beamforming":[48],"is":[49,52],"not":[50],"known.This":[51],"an":[53,61,68],"important":[54],"question":[55],"be":[57,115],"answered":[58],"especially":[59],"automotive":[62,83],"environment,":[63],"for":[64],"design":[66],"efficient":[69],"human-vehicle":[70],"computer":[71],"interface.We":[72],"perform":[73],"a":[74,81],"variety":[75],"experiments":[79],"on":[80],"challenging":[82],"dataset":[85],"and":[86],"results":[87],"show":[88,107],"that":[89,108],"synchronous":[90],"HMM-based":[91],"audio-visual":[92],"fusion":[93],"traditional":[96],"single":[97],"well":[99],"techniques.We":[105],"also":[106],"further":[109],"improvement":[110],"obtained":[116],"by":[117],"fusing":[118],"speech-enhanced":[119],"audio":[120],"with":[121],"modality,":[124],"demonstrating":[125],"complementary":[127],"nature":[128],"two":[131],"robust":[132],"approaches.":[135]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}