{"id":"https://openalex.org/W27510056","doi":"https://doi.org/10.21437/interspeech.2009-358","title":"Reduced complexity equalization of lombard effect for speech recognition in noisy adverse environments","display_name":"Reduced complexity equalization of lombard effect for speech recognition in noisy adverse environments","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W27510056","doi":"https://doi.org/10.21437/interspeech.2009-358","mag":"27510056"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-358","doi":"https://doi.org/10.21437/interspeech.2009-358","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-358","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","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":"Interspeech 2009","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 Bo\u0159il","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4692,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54065858,"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":"1243","last_page":"1246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937000274658203,"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":0.9937000274658203,"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":0.006300000008195639,"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":0.996999979019165},{"id":"https://openalex.org/keywords/speech-recognition-in-noise","display_name":"speech recognition in noise","score":0.6679999828338623},{"id":"https://openalex.org/keywords/computational-cost-reduction","display_name":"computational complexity reduction","score":0.7480000257492065},{"id":"https://openalex.org/keywords/frequency-transformation","display_name":"frequency transformation","score":0.8009999990463257},{"id":"https://openalex.org/keywords/background-noise-robustness","display_name":"background noise robustness","score":0.6349999904632568},{"id":"https://openalex.org/keywords/connected-digit-recognition","display_name":"connected digit recognition","score":0.6060000061988831}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8240054845809937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7799162864685059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7416853308677673},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5870875120162964},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5226780772209167},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5148636102676392},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.48611950874328613},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4692889153957367},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.44771072268486023},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42967474460601807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35123130679130554},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3071702718734741},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14307621121406555},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08821025490760803},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-358","doi":"https://doi.org/10.21437/interspeech.2009-358","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-358","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","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":"Interspeech 2009","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2004826498","https://openalex.org/W2072328708","https://openalex.org/W2096503735","https://openalex.org/W2115908232","https://openalex.org/W2121892718","https://openalex.org/W2147542668","https://openalex.org/W2151484683","https://openalex.org/W2155082225"],"related_works":["https://openalex.org/W7095117330","https://openalex.org/W7098336395","https://openalex.org/W2117486215","https://openalex.org/W2115908232","https://openalex.org/W7098961708","https://openalex.org/W7100294164","https://openalex.org/W7097135127","https://openalex.org/W882281826","https://openalex.org/W4302342720","https://openalex.org/W7097168528"],"abstract_inverted_index":{"In":[0,109,146],"real-world":[1],"adverse":[2],"environments,":[3],"speech":[4,14,33,80,205],"signal":[5],"corruption":[6],"by":[7,18],"background":[8,194],"noise,":[9],"microphone":[10],"channel":[11],"variations,":[12],"and":[13,73,122,157,197],"production":[15],"adjustments":[16],"introduced":[17,156],"speakers":[19],"in":[20,96,162,190],"an":[21,148],"effort":[22],"to":[23,46,85,100,128,136,159,183],"communicate":[24],"efficiently":[25],"over":[26],"noise":[27,196],"(Lombard":[28],"effect)":[29],"severely":[30],"impact":[31],"automatic":[32],"recognition":[34],"(ASR)":[35],"performance.":[36,145],"Recently,":[37],"a":[38,76,91,112,115,123],"set":[39,116],"of":[40,49,60,78,93,117,193],"unsupervised":[41],"techniques":[42],"reducing":[43],"ASR":[44,107,138,161],"sensitivity":[45],"these":[47],"sources":[48],"distortion":[50],"have":[51,82],"been":[52,83],"presented,":[53],"with":[54,75],"the":[55,106,131,174],"main":[56],"focus":[57],"on":[58,173],"equalization":[59],"Lombard":[61,176,203],"effect":[62],"(LE).":[63],"The":[64,169,180],"algorithms":[65],"performing":[66],"maximum-likelihood":[67],"spectral":[68],"transformation,":[69,210],"cepstral":[70,211],"dynamics":[71],"normalization,":[72],"decoding":[74,103,139],"codebook":[77,150,207],"noisy":[79],"models":[81,121],"shown":[84,127,158],"outperform":[86],"conventional":[87],"methods,":[88],"however,":[89],"at":[90],"cost":[92],"considerable":[94],"increase":[95],"computational":[97,132],"complexity":[98],"due":[99],"required":[101],"numerous":[102],"passes":[104],"through":[105],"models.":[108],"this":[110],"study,":[111],"scheme":[113],"utilizing":[114],"speech-in-noise":[118],"Gaussian":[119],"mixture":[120],"neutral/LE":[124,185],"classifier":[125],"is":[126,155,171,182],"substantially":[129],"decrease":[130],"load":[133],"(from":[134],"14":[135],"2\u20104":[137],"passes)":[140],"while":[141],"preserving":[142],"overall":[143],"system":[144],"addition,":[147],"extended":[149],"capturing":[151],"multiple":[152],"environmental":[153],"noises":[154],"improve":[160],"changing":[163],"environments":[164],"(8.2\u201049.2%":[165],"absolute":[166],"WER":[167],"improvement).":[168],"evaluation":[170],"performed":[172],"Czech":[175],"Speech":[177],"Database":[178],"(CLSD\u201805).":[179],"task":[181],"recognize":[184],"connected":[186],"digit":[187],"strings":[188],"presented":[189],"different":[191],"levels":[192],"car":[195],"Aurora":[198],"2":[199],"noises.":[200],"Index":[201],"Terms:":[202],"effect,":[204],"recognition,":[206],"decoding,":[208],"frequency":[209],"normalization":[212]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2016-06-24T00:00:00"}