{"id":"https://openalex.org/W2051360208","doi":"https://doi.org/10.1109/tsp.2013.6613979","title":"Audio-visual speech recognition in noisy audio environments","display_name":"Audio-visual speech recognition in noisy audio environments","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2051360208","doi":"https://doi.org/10.1109/tsp.2013.6613979","mag":"2051360208"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2013.6613979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2013.6613979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 36th International Conference on Telecommunications and Signal Processing (TSP)","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/A5018875802","display_name":"Karel Pale\u010dek","orcid":"https://orcid.org/0000-0003-0693-6603"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Karel Palecek","raw_affiliation_strings":["The Institute of Information Technology and Electronics, Technical University of Liberec","Inst. of Inf. Technol. & Electron., Tech. Univ. of Liberec, Liberec, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Information Technology and Electronics, Technical University of Liberec","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"Inst. of Inf. Technol. & Electron., Tech. Univ. of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055881800","display_name":"Josef Chaloupka","orcid":"https://orcid.org/0000-0001-6536-1219"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Josef Chaloupka","raw_affiliation_strings":["The Institute of Information Technology and Electronics, Technical University of Liberec","Inst. of Inf. Technol. & Electron., Tech. Univ. of Liberec, Liberec, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Information Technology and Electronics, Technical University of Liberec","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"Inst. of Inf. Technol. & Electron., Tech. Univ. of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2545,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88441109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"484","last_page":"487"},"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":0.9958999752998352,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7761186361312866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7660214900970459},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.7397849559783936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5789227485656738},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5551297664642334},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5234048962593079},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5230551362037659},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.4849541187286377},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.46762615442276},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4568442106246948},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.45062828063964844},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42798101902008057},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34216248989105225},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3105185627937317},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.305828720331192},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10186195373535156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7761186361312866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7660214900970459},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.7397849559783936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5789227485656738},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5551297664642334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5234048962593079},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5230551362037659},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.4849541187286377},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.46762615442276},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4568442106246948},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.45062828063964844},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42798101902008057},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34216248989105225},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3105185627937317},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.305828720331192},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10186195373535156},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsp.2013.6613979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2013.6613979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 36th International Conference on Telecommunications and Signal Processing (TSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W43954047","https://openalex.org/W82494927","https://openalex.org/W131634123","https://openalex.org/W142803501","https://openalex.org/W1498911878","https://openalex.org/W1519520670","https://openalex.org/W1603828868","https://openalex.org/W1769974409","https://openalex.org/W1974387177","https://openalex.org/W2051057783","https://openalex.org/W2082308025","https://openalex.org/W2096391593","https://openalex.org/W2097711399","https://openalex.org/W2121973264","https://openalex.org/W6601810651","https://openalex.org/W6603350892","https://openalex.org/W6629981029","https://openalex.org/W6635867316"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W1984921740","https://openalex.org/W2070982348","https://openalex.org/W2365485488","https://openalex.org/W2910493550","https://openalex.org/W137020845","https://openalex.org/W1911859126","https://openalex.org/W642007152"],"abstract_inverted_index":{"It":[0],"is":[1,26],"a":[2,29,66],"well-known":[3],"fact":[4],"that":[5],"the":[6,13,91,104,109,125],"visual":[7,32,56,61,80],"part":[8],"of":[9,23,31,69],"speech":[10,43,62,99],"can":[11],"improve":[12],"resulting":[14],"recognition":[15,44,100],"rate":[16],"mainly":[17],"in":[18,40,124],"noisy":[19],"conditions.":[20],"Main":[21],"goal":[22],"this":[24],"work":[25],"to":[27,38],"find":[28],"set":[30],"features":[33,57,81,89],"which":[34],"would":[35],"be":[36],"possible":[37],"use":[39],"our":[41],"audio-visual":[42,98],"systems.":[45],"Discrete":[46],"Cosine":[47],"Transform":[48],"(DCT)":[49],"and":[50,75,115],"Active":[51],"Appearance":[52],"Model":[53],"(AAM)":[54],"based":[55],"are":[58,82,101,128],"extracted":[59],"from":[60,97,106],"signals,":[63],"enhanced":[64],"by":[65,90],"simplified":[67],"variant":[68],"Hierarchical":[70],"Linear":[71],"Discriminant":[72],"Analysis":[73],"(HiLDA)":[74],"normalized":[76],"across":[77],"speakers.":[78],"The":[79,95],"then":[83],"combined":[84],"with":[85,103],"standard":[86],"MFCC":[87],"audio":[88,126],"middle":[92],"fusion":[93],"method.":[94],"results":[96,105],"compared":[102],"experiments":[107],"where":[108],"log-spectra":[110],"minimum":[111],"mean":[112],"square":[113],"error":[114],"multiband":[116],"spectral":[117],"subtraction":[118],"methods":[119],"for":[120],"reducing":[121],"additive":[122],"noise":[123],"signal":[127],"used.":[129]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}