{"id":"https://openalex.org/W1498717522","doi":"https://doi.org/10.1109/icassp.2015.7178819","title":"Exemplar-based speech enhancement for deep neural network based automatic speech recognition","display_name":"Exemplar-based speech enhancement for deep neural network based automatic speech recognition","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1498717522","doi":"https://doi.org/10.1109/icassp.2015.7178819","mag":"1498717522"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178819","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/handle/123456789/484792","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/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/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":"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":4,"corresponding_author_ids":["https://openalex.org/A5067322015"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":3.1836,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92154385,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"401","issue":null,"first_page":"4485","last_page":"4489"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.7813904285430908},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7557107210159302},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5627576112747192},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5232497453689575},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4972684681415558},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47048357129096985},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4460658133029938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42889833450317383},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42200398445129395},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06785154342651367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813904285430908},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7557107210159302},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5627576112747192},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5232497453689575},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4972684681415558},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47048357129096985},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4460658133029938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42889833450317383},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42200398445129395},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06785154342651367}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2015.7178819","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.712.3369","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.712.3369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tut.fi/sgn/arg/music/tuomasv/dbaby_icassp2015.pdf","raw_type":"text"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/484792","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/484792","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":"IEEE international conference on acoustics, speech, and signal processing - ICASSP\u20192015, Brisbane, Australia, 19-24 April 2015","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/484792","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/484792","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":"IEEE international conference on acoustics, speech, and signal processing - ICASSP\u20192015, Brisbane, Australia, 19-24 April 2015","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W146976060","https://openalex.org/W1501109341","https://openalex.org/W1524333225","https://openalex.org/W1729878635","https://openalex.org/W1902027874","https://openalex.org/W2016430046","https://openalex.org/W2062164080","https://openalex.org/W2121973264","https://openalex.org/W2129901640","https://openalex.org/W2131342762","https://openalex.org/W2141520175","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2394967684","https://openalex.org/W2396455701","https://openalex.org/W2403608536","https://openalex.org/W2747655461","https://openalex.org/W4243044416","https://openalex.org/W4255019833","https://openalex.org/W6631362777","https://openalex.org/W6679429981","https://openalex.org/W6711908631","https://openalex.org/W6713866305","https://openalex.org/W6742785727"],"related_works":["https://openalex.org/W3175075966","https://openalex.org/W2764005420","https://openalex.org/W2181728593","https://openalex.org/W1576113739","https://openalex.org/W3000194274","https://openalex.org/W1679636228","https://openalex.org/W3015358918","https://openalex.org/W2394461504","https://openalex.org/W2988392183","https://openalex.org/W3135356379"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"(DNN)":[3],"based":[4],"acoustic":[5],"modelling":[6],"has":[7],"been":[8],"successfully":[9],"used":[10],"for":[11,49,107],"a":[12,46,61,74,85],"variety":[13],"of":[14,64,76,117,147],"automatic":[15],"speech":[16,39,57,103,108],"recognition":[17],"(ASR)":[18],"tasks,":[19],"thanks":[20],"to":[21,24,84,99],"its":[22],"ability":[23],"learn":[25],"higher-level":[26],"information":[27],"using":[28,42,114],"multiple":[29],"hidden":[30],"layers.":[31],"This":[32],"paper":[33],"investigates":[34],"the":[35,55,79,93,102,121,135,145,148],"recently":[36],"proposed":[37],"exemplar-based":[38],"enhancement":[40],"technique":[41],"coupled":[43,86],"dictionaries":[44],"as":[45,60],"pre-processing":[47,141],"stage":[48],"DNN-based":[50],"systems.":[51],"In":[52,110],"this":[53,111],"setting,":[54],"noisy":[56],"is":[58],"decomposed":[59],"weighted":[62],"sum":[63],"atoms":[65],"in":[66,92],"an":[67],"input":[68,115],"dictionary":[69,88,116],"containing":[70,89],"exemplars":[71,90,118],"sampled":[72,91,119],"from":[73,120],"domain":[75,98],"choice,":[77],"and":[78,104,126,155],"resulting":[80],"weights":[81],"are":[82,130],"applied":[83],"output":[87],"short-time":[94],"Fourier":[95],"transform":[96],"(STFT)":[97],"directly":[100],"obtain":[101],"noise":[105],"estimates":[106],"enhancement.":[109],"work,":[112],"settings":[113],"STFT,":[122],"Mel-integrated":[123],"magnitude":[124],"STFT":[125],"modulation":[127],"envelope":[128],"spectra":[129],"evaluated.":[131],"Experiments":[132],"performed":[133],"on":[134],"AURORA-4":[136],"database":[137],"revealed":[138],"that":[139],"these":[140],"stages":[142],"can":[143],"improve":[144],"performance":[146],"DNN-HMM-based":[149],"ASR":[150],"systems":[151],"with":[152],"both":[153],"clean":[154],"multi-condition":[156],"training.":[157]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}