{"id":"https://openalex.org/W2016363830","doi":"https://doi.org/10.1109/slt.2014.7078628","title":"Exemplar-based noise robust automatic speech recognition using modulation spectrogram features","display_name":"Exemplar-based noise robust automatic speech recognition using modulation spectrogram features","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2016363830","doi":"https://doi.org/10.1109/slt.2014.7078628","mag":"2016363830"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/handle/123456789/479362","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067322015","display_name":"Deepak Baby","orcid":"https://orcid.org/0000-0001-8935-9068"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Deepak Baby","raw_affiliation_strings":["Department ESAT, KU Leuven, Belgium","[Department ESAT, KU Leuven, Belgium]"],"affiliations":[{"raw_affiliation_string":"Department ESAT, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"[Department ESAT, KU Leuven, Belgium]","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Finland","Department of Signal Processing Tampere University of Technology, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Signal Processing Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109012430","display_name":"Jort F. Gemmeke","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jort F. Gemmeke","raw_affiliation_strings":["Department ESAT, KU Leuven, Belgium","[Department ESAT, KU Leuven, Belgium]"],"affiliations":[{"raw_affiliation_string":"Department ESAT, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"[Department ESAT, KU Leuven, Belgium]","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104103091","display_name":"Tom Barker","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tom Barker","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Finland","Department of Signal Processing Tampere University of Technology, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Signal Processing Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hugo Van hamme","raw_affiliation_strings":["Department ESAT, KU Leuven, Belgium","[Department ESAT, KU Leuven, Belgium]"],"affiliations":[{"raw_affiliation_string":"Department ESAT, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"[Department ESAT, KU Leuven, Belgium]","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067322015"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":2.5216,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.9064591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"519","last_page":"524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9965000152587891,"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/spectrogram","display_name":"Spectrogram","score":0.9064008593559265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7433574199676514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7216577529907227},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.595679759979248},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.5801752805709839},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5248762965202332},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5001091957092285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4910461902618408},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46715134382247925},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4605734348297119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45038464665412903},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14964362978935242},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12056100368499756},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0786806046962738}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9064008593559265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433574199676514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7216577529907227},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.595679759979248},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.5801752805709839},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5248762965202332},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5001091957092285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4910461902618408},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46715134382247925},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4605734348297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45038464665412903},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14964362978935242},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12056100368499756},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0786806046962738},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2014.7078628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/479362","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/479362","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Spoken language technology workshop - SLT 2014, South Lake Tahoe, Nevada, USA, 7-10 December 2014","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/479362","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/479362","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Spoken language technology workshop - SLT 2014, South Lake Tahoe, Nevada, USA, 7-10 December 2014","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1729878635","https://openalex.org/W1902027874","https://openalex.org/W1904457459","https://openalex.org/W1964538581","https://openalex.org/W1968906488","https://openalex.org/W1992272902","https://openalex.org/W2016430046","https://openalex.org/W2082795204","https://openalex.org/W2104448323","https://openalex.org/W2120847449","https://openalex.org/W2126597753","https://openalex.org/W2128653836","https://openalex.org/W2129901640","https://openalex.org/W2137041883","https://openalex.org/W2137075158","https://openalex.org/W2141520175","https://openalex.org/W2150863656","https://openalex.org/W2152051032","https://openalex.org/W2334833135","https://openalex.org/W2336741987","https://openalex.org/W2402267837","https://openalex.org/W2402404264","https://openalex.org/W2403608536","https://openalex.org/W2490695385","https://openalex.org/W2584505851","https://openalex.org/W4255019833","https://openalex.org/W4256399001","https://openalex.org/W6631362777","https://openalex.org/W6703444193"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2944691285"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,112],"novel":[3],"exemplar-based":[4],"feature":[5],"enhancement":[6],"method":[7,78],"for":[8,47,56],"automatic":[9],"speech":[10,52],"recognition":[11],"which":[12,68,100,115,127],"uses":[13,101],"coupled":[14],"dictionaries:":[15],"an":[16,29],"input":[17,42,106],"dictionary":[18,31],"containing":[19],"atoms":[20,33],"sampled":[21],"in":[22,34,104,128],"the":[23,35,73,82,98,105,117,120,124,135],"modulation":[24,43],"(envelope)":[25],"spectrogram":[26],"domain":[27],"and":[28,53,55,84,87,119],"output":[30,64],"with":[32,59],"Mel":[36,102],"or":[37],"full-resolution":[38],"frequency":[39],"domain.":[40],"The":[41,63,76,108],"representation":[44,65],"is":[45,66],"chosen":[46],"its":[48,57],"separation":[49],"properties":[50],"of":[51],"noise":[54],"relation":[58],"human":[60],"auditory":[61],"processing.":[62],"one":[67],"can":[69],"be":[70],"processed":[71],"by":[72],"ASR":[74],"back-end.":[75],"proposed":[77,121],"was":[79],"investigated":[80],"on":[81,123],"AURORA-2":[83,125],"AURORA-4":[85],"databases":[86],"improved":[88],"word":[89],"error":[90],"rates":[91],"(WER)":[92],"were":[93],"obtained":[94],"when":[95],"compared":[96],"to":[97],"system":[99,114],"features":[103],"exemplars.":[107],"paper":[109],"also":[110,130],"proposes":[111],"hybrid":[113],"combines":[116],"baseline":[118],"algorithm":[122],"database":[126],"turn":[129],"yielded":[131],"improvement":[132],"over":[133],"both":[134],"algorithms.":[136]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
