{"id":"https://openalex.org/W2155633365","doi":"https://doi.org/10.1109/icassp.1997.596073","title":"Spectral subtraction and RASTA-filtering in text-dependent HMM-based speaker verification","display_name":"Spectral subtraction and RASTA-filtering in text-dependent HMM-based speaker verification","publication_year":2002,"publication_date":"2002-11-22","ids":{"openalex":"https://openalex.org/W2155633365","doi":"https://doi.org/10.1109/icassp.1997.596073","mag":"2155633365"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1997.596073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1997.596073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1997 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"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/A5054824570","display_name":"Daniel Hardt","orcid":"https://orcid.org/0000-0001-6041-1475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Hardt","raw_affiliation_strings":["Institute of Telecommunication and Theoretical Electrical Engineering, Technical University Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Telecommunication and Theoretical Electrical Engineering, Technical University Berlin, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057854579","display_name":"Klaus Fellbaum","orcid":null},"institutions":[{"id":"https://openalex.org/I51783024","display_name":"Brandenburg University of Technology Cottbus-Senftenberg","ror":"https://ror.org/02wxx3e24","country_code":"DE","type":"education","lineage":["https://openalex.org/I51783024"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"K. Fellbaum","raw_affiliation_strings":["Communications Engineering, Brandenburg University of Technology, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Engineering, Brandenburg University of Technology, Germany","institution_ids":["https://openalex.org/I51783024"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"867","last_page":"870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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":0.996999979019165,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.809749960899353},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7943577170372009},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7259995341300964},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5712072849273682},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5426966547966003},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4976177513599396},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4799076020717621},{"id":"https://openalex.org/keywords/subtraction","display_name":"Subtraction","score":0.46727100014686584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4566875696182251},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.45025742053985596},{"id":"https://openalex.org/keywords/background-subtraction","display_name":"Background subtraction","score":0.4380868971347809},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41815805435180664},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2038811445236206},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11331820487976074},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.06738060712814331}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.809749960899353},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7943577170372009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7259995341300964},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5712072849273682},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5426966547966003},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4976177513599396},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4799076020717621},{"id":"https://openalex.org/C68060419","wikidata":"https://www.wikidata.org/wiki/Q40754","display_name":"Subtraction","level":2,"score":0.46727100014686584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4566875696182251},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.45025742053985596},{"id":"https://openalex.org/C32653426","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Background subtraction","level":3,"score":0.4380868971347809},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41815805435180664},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2038811445236206},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11331820487976074},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.06738060712814331},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"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.1997.596073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1997.596073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1997 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W157872538","https://openalex.org/W2090861223","https://openalex.org/W2135984923","https://openalex.org/W2189335403","https://openalex.org/W3184634567","https://openalex.org/W3217496233"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2188430267","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W1494724239"],"abstract_inverted_index":{"In":[0,17],"real":[1],"text-dependent":[2],"telephone-based":[3],"speaker":[4,25],"verification":[5,26],"systems,":[6],"both,":[7],"additive":[8],"and":[9,47,67],"convolutional":[10],"noise":[11,31,137],"influence":[12],"the":[13,65,74,81,84,94,103,112,115,118,146,149,153,163],"error":[14],"rate":[15],"considerably.":[16],"this":[18],"paper,":[19],"different":[20],"procedures":[21],"which":[22,61,168],"make":[23],"a":[24,68,128],"system":[27,66,147],"more":[28],"robust":[29],"against":[30],"are":[32],"compared.":[33],"We":[34],"either":[35],"use":[36],"spectral":[37,50,53,166],"subtraction":[38,54],"in":[39,176],"addition":[40],"to":[41,64,99,144,172],"MFCC-feature":[42],"extraction":[43],"or":[44],"only":[45],"PLP":[46],"RASTA-PLP":[48],"(without":[49],"subtraction).":[51],"Considering":[52],"two":[55],"modifications":[56],"were":[57],"examined:":[58],"one":[59,70],"version":[60,79],"was":[62],"preconnected":[63],"second":[69],"being":[71],"integrated":[72],"into":[73],"MFCC":[75,95],"computation.":[76],"The":[77],"first":[78,125],"has":[80,169],"advantage":[82],"that":[83],"window":[85],"length":[86],"can":[87],"be":[88,173],"chosen":[89],"independently":[90],"of":[91,93,117,136,152,165],"those":[92],"procedure.":[96],"This":[97,158],"led":[98],"better":[100],"results.":[101],"However,":[102],"most":[104],"effective":[105,175],"procedure":[106,159],"for":[107],"telephone":[108],"speech":[109,178],"data":[110],"is":[111,122,160],"J-RASTA-PLP,":[113],"but":[114],"estimation":[116,151],"optimal":[119],"J":[120,130,154],"factor":[121,131,155],"difficult.":[123],"At":[124],"we":[126,140],"used":[127],"fixed":[129],"based":[132,161],"on":[133,162],"off-line":[134],"measurement":[135],"power.":[138],"Finally,":[139],"performed":[141],"some":[142],"experiments":[143],"optimize":[145],"with":[148],"adaptive":[150],"during":[156],"utterance.":[157],"method":[164],"mapping":[167],"been":[170],"shown":[171],"very":[174],"automatic":[177],"recognition.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}