{"id":"https://openalex.org/W2108963403","doi":"https://doi.org/10.1109/icassp.1992.225921","title":"Non-linear spectral subtraction (NSS) and hidden Markov models for robust speech recognition in car noise environments","display_name":"Non-linear spectral subtraction (NSS) and hidden Markov models for robust speech recognition in car noise environments","publication_year":1992,"publication_date":"1992-01-01","ids":{"openalex":"https://openalex.org/W2108963403","doi":"https://doi.org/10.1109/icassp.1992.225921","mag":"2108963403"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1992.225921","doi":"https://doi.org/10.1109/icassp.1992.225921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1992.225921","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":"[Proceedings] ICASSP-92: 1992 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/A5068035341","display_name":"P. Lockwood","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. Lockwood","raw_affiliation_strings":["Matra Communication, Bois D'Arcy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Matra Communication, Bois D'Arcy, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011123851","display_name":"J\u00e9r\u00f4me Boudy","orcid":"https://orcid.org/0000-0002-0306-091X","observed_orcids":["https://orcid.org/0000-0002-0306-091X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Boudy","raw_affiliation_strings":["Matra Communication, Bois D'Arcy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Matra Communication, Bois D'Arcy, France","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"M. Blanchet","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Blanchet","raw_affiliation_strings":["Matra Communication, Bois D'Arcy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Matra Communication, Bois D'Arcy, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5485,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.92283426,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"265","last_page":"268 vol.1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9932000041007996,"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":0.9932000041007996,"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":0.0066999997943639755,"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":0.0,"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/hidden-markov-models","display_name":"hidden Markov models","score":0.9399999976158142},{"id":"https://openalex.org/keywords/robust-speech-recognition","display_name":"robust speech recognition","score":0.9760000109672546},{"id":"https://openalex.org/keywords/car-noise","display_name":"car noise","score":0.7889999747276306},{"id":"https://openalex.org/keywords/speaker-dependent-speech-recognition","display_name":"speaker-dependent recognition","score":0.7590000033378601},{"id":"https://openalex.org/keywords/training-test-mismatch","display_name":"training-test mismatch","score":0.5230000019073486},{"id":"https://openalex.org/keywords/dynamic-characteristics","display_name":"dynamic characteristics","score":0.9610000252723694},{"id":"https://openalex.org/keywords/bandlimited-signals","display_name":"band-limited signals","score":0.6970000267028809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233455181121826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7195108532905579},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.708489179611206},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5451738834381104},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5398013591766357},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4969828426837921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4843800961971283},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4335886538028717},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42592257261276245},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2642698884010315},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1992.225921","doi":"https://doi.org/10.1109/icassp.1992.225921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1992.225921","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":"[Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W157872538","https://openalex.org/W1994396704","https://openalex.org/W1997418877","https://openalex.org/W2018228148","https://openalex.org/W2049918796","https://openalex.org/W2077313914","https://openalex.org/W2090861223","https://openalex.org/W2135672233","https://openalex.org/W2146135592","https://openalex.org/W2148154194","https://openalex.org/W2152716564","https://openalex.org/W2163632146","https://openalex.org/W2166055581"],"related_works":["https://openalex.org/W2018228148","https://openalex.org/W7052188876","https://openalex.org/W2157702502","https://openalex.org/W2146507015","https://openalex.org/W343425725","https://openalex.org/W2113703812","https://openalex.org/W7018129254","https://openalex.org/W149665903","https://openalex.org/W2506156642","https://openalex.org/W1679514224"],"abstract_inverted_index":{"The":[0,34,98],"authors":[1,35,99],"address":[2],"the":[3,17,22],"problem":[4],"of":[5,61,69,73,78],"speaker-dependent":[6],"discrete":[7],"utterance":[8],"recognition":[9,117],"in":[10,31,113],"noise.":[11],"Special":[12],"reference":[13],"is":[14,53,119],"made":[15],"to":[16,21,110],"mismatch":[18],"effects":[19],"due":[20],"fact":[23],"that":[24,101],"training":[25,77],"and":[26,41,76,130],"testing":[27],"are":[28,58,88],"carried":[29],"out":[30],"different":[32],"environments.":[33],"extend":[36],"their":[37],"previous":[38],"work":[39],"(Lockwood":[40],"Boudy,":[42],"1991)":[43],"where":[44],"a":[45,81,106,126,131],"robust":[46],"hidden":[47],"Markov":[48],"model":[49],"(HMM)":[50],"training/recognition":[51],"framework":[52],"proposed.":[54],"Several":[55],"new":[56],"aspects":[57],"introduced:":[59],"use":[60,72],"enhanced":[62],"nonlinear":[63],"spectral":[64],"subtraction":[65],"(NSS)":[66],"schemes,":[67],"introduction":[68],"root-MFCC":[70,132],"parameters,":[71],"dynamic":[74,82,133],"features,":[75],"HMMs":[79],"by":[80],"inference":[83],"scheme":[84],"(DIHMM).":[85],"These":[86],"enhancements":[87],"discussed":[89],"from":[90,108],"tests":[91],"performed":[92],"on":[93,122],"bandlimited":[94],"signals":[95],"(200-3000":[96],"Hz).":[97],"show":[100],"these":[102],"various":[103],"optimizations":[104],"allow":[105],"rise":[107],"20%":[109],"over":[111],"99%":[112],"performance.":[114],"A":[115],"93%":[116],"rate":[118],"already":[120],"achievable":[121],"raw":[123],"data":[124],"using":[125],"weighted":[127],"modified":[128],"projection":[129],"representation.>":[134]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}