{"id":"https://openalex.org/W2115908232","doi":"https://doi.org/10.1109/icassp.2009.4960489","title":"Unsupervised equalization of Lombard effect for speech recognition in noisy adverse environment","display_name":"Unsupervised equalization of Lombard effect for speech recognition in noisy adverse environment","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2115908232","doi":"https://doi.org/10.1109/icassp.2009.4960489","mag":"2115908232"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960489","doi":"https://doi.org/10.1109/icassp.2009.4960489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960489","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"volume":null,"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/A5009895165","display_name":"Hynek Bo\u0159il","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hynek Boril","raw_affiliation_strings":["Center of Robust Speech Systems, Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, USA","Center for Robust Speech Systems, Erik Jonsson School of Engineering & Computer Science, The University of Texas at Dallas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Robust Speech Systems, Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems, Erik Jonsson School of Engineering & Computer Science, The University of Texas at Dallas, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["University of Texas, Dallas, USA","Center for Robust Speech Systems, Erik Jonsson School of Engineering & Computer Science, The University of Texas at Dallas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Dallas, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems, Erik Jonsson School of Engineering & Computer Science, The University of Texas at Dallas, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":1.1731,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79119584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"3937","last_page":"3940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9951000213623047,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9951000213623047,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.004800000227987766,"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/T10403","display_name":"Phonetics and Phonology Research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lombard-effect","display_name":"Lombard effect","score":1.0},{"id":"https://openalex.org/keywords/speech-recognition-in-noise","display_name":"speech recognition in noise","score":0.5789999961853027},{"id":"https://openalex.org/keywords/frequency-domain-equalization","display_name":"frequency-domain equalization","score":0.7879999876022339},{"id":"https://openalex.org/keywords/car-noise","display_name":"car noise","score":0.5249999761581421},{"id":"https://openalex.org/keywords/word-error-rate-reduction","display_name":"word error rate reduction","score":0.8600000143051147},{"id":"https://openalex.org/keywords/perceptual-linear-prediction","display_name":"perceptual linear prediction","score":0.6480000019073486}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8011196255683899},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.652088463306427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6506480574607849},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5896727442741394},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5551462769508362},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.5038256049156189},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.440653532743454},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4351864457130432},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4317900836467743},{"id":"https://openalex.org/C2777185736","wikidata":"https://www.wikidata.org/wiki/Q7265603","display_name":"QUIET","level":2,"score":0.4132440686225891},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3506321907043457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3078032433986664},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.19921335577964783},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960489","doi":"https://doi.org/10.1109/icassp.2009.4960489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960489","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.301.5026","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.5026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.utdallas.edu/~hynek/pdfs/ICASSP09_1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W54525843","https://openalex.org/W1562705272","https://openalex.org/W2004826498","https://openalex.org/W2045036776","https://openalex.org/W2050693797","https://openalex.org/W2072328708","https://openalex.org/W2105885996","https://openalex.org/W2106119541","https://openalex.org/W2147542668","https://openalex.org/W2155082225","https://openalex.org/W2402261002","https://openalex.org/W6675836319"],"related_works":["https://openalex.org/W7098961708","https://openalex.org/W2117486215","https://openalex.org/W7098336395","https://openalex.org/W27510056","https://openalex.org/W7095117330","https://openalex.org/W7097135127","https://openalex.org/W7100294164","https://openalex.org/W882281826","https://openalex.org/W4302342720","https://openalex.org/W2038875793"],"abstract_inverted_index":{"When":[0],"exposed":[1],"to":[2,10,22,74,151],"environmental":[3],"noise,":[4,110],"speakers":[5],"adjust":[6],"their":[7],"speech":[8,29,56,148],"production":[9],"maintain":[11],"intelligible":[12],"communication.":[13],"This":[14],"phenomenon,":[15],"called":[16],"Lombard":[17],"effect":[18],"(LE),":[19],"is":[20],"known":[21],"considerably":[23],"impact":[24,45],"the":[25,44,111,152],"performance":[26],"of":[27,46,54,69,91,107,128,139],"automatic":[28],"recognition":[30,97],"(ASR)":[31],"systems.":[32],"In":[33,95],"this":[34],"study,":[35],"novel":[36],"frequency":[37],"and":[38,130,135,138,141,146,161,164],"cepstral":[39,70,162],"domain":[40],"equalizations":[41],"that":[42],"reduce":[43],"LE":[47,55,136,147],"on":[48,99,123],"ASR":[49,61],"are":[50,57,72,83],"proposed.":[51],"Short-time":[52],"spectra":[53],"transformed":[58],"towards":[59],"neutral":[60,134,145],"models":[62],"in":[63,85,104,118],"a":[64,75,86,89,96],"maximum":[65],"likelihood":[66],"fashion.":[67],"Dynamics":[68],"coefficients":[71,160],"normalized":[73],"constant":[76],"range":[77],"using":[78],"quantile":[79],"estimations.":[80],"The":[81],"algorithms":[82],"incorporated":[84],"recognizer":[87],"employing":[88,155],"codebook":[90],"noisy":[92],"acoustic":[93],"models.":[94],"task":[98],"connected":[100],"Czech":[101],"digits":[102],"presented":[103],"various":[105],"levels":[106],"background":[108],"car":[109],"resulting":[112],"system":[113,154],"provides":[114],"an":[115],"absolute":[116],"reduction":[117],"word":[119],"error":[120],"rate":[121],"(WER)":[122],"10":[124],"dB":[125],"SNR":[126],"data":[127],"8.7%":[129,140],"37.7%":[131],"for":[132,143],"female":[133],"speech,":[137],"32.8%":[142],"male":[144],"when":[149],"compared":[150],"baseline":[153],"perceptual":[156],"linear":[157],"prediction":[158],"(PLP)":[159],"mean":[163],"variance":[165],"normalization.":[166]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}