{"id":"https://openalex.org/W136303559","doi":"https://doi.org/10.21437/interspeech.2004-634","title":"Active perception: using a priori knowledge from clean speech models to ignore non-target features","display_name":"Active perception: using a priori knowledge from clean speech models to ignore non-target features","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W136303559","doi":"https://doi.org/10.21437/interspeech.2004-634","mag":"136303559"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-634","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"article","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/A5111462069","display_name":"Bert Cranen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bert Cranen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091615805","display_name":"Johan de Veth","orcid":null},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Johan de Veth","raw_affiliation_strings":["Radboud University Nijmegen#TAB#"],"affiliations":[{"raw_affiliation_string":"Radboud University Nijmegen#TAB#","institution_ids":["https://openalex.org/I145872427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111462069"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2804,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51342897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2081","last_page":"2084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.8265120983123779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269563674926758},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6814783811569214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5799234509468079},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5213964581489563},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4877620339393616},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.48619717359542847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4806634187698364},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.46730872988700867},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.45502620935440063},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43268200755119324},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38317394256591797},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.380990594625473},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3778291642665863},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12782689929008484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11563152074813843}],"concepts":[{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.8265120983123779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269563674926758},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6814783811569214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5799234509468079},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5213964581489563},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4877620339393616},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.48619717359542847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4806634187698364},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.46730872988700867},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.45502620935440063},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43268200755119324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38317394256591797},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.380990594625473},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3778291642665863},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12782689929008484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11563152074813843},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-634","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W68871563","https://openalex.org/W88081813","https://openalex.org/W289804034","https://openalex.org/W1504344060","https://openalex.org/W2013020033","https://openalex.org/W2050364914","https://openalex.org/W2074354966","https://openalex.org/W2089617642","https://openalex.org/W2128653836","https://openalex.org/W2132542731","https://openalex.org/W2296039540"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Making":[0],"ASR":[1],"noise":[2,36,40],"robust":[3],"requires":[4],"a":[5,50,56],"form":[6],"of":[7,15,35,92,115,124,141],"data":[8,99],"normalisation":[9],"to":[10,30,83,96,109],"ensure":[11],"that":[12,53,101,145],"the":[13,19,33,39,43,79,93,116,122,127,133,142,152],"distributions":[14],"acoustic":[16],"features":[17],"in":[18,60,77],"training":[20],"and":[21],"test":[22],"condition":[23],"look":[24],"similar.":[25],"Usually,":[26],"it":[27],"is":[28],"attempted":[29],"compensate":[31],"for":[32,132],"impact":[34],"by":[37,75],"estimating":[38],"characteristics":[41],"from":[42],"signal.":[44],"In":[45,121],"this":[46],"paper":[47],"we":[48],"explore":[49],"new":[51,94,153],"method":[52,95],"builds":[54],"on":[55,150],"priori":[57],"knowledge":[58],"stored":[59],"clean":[61,70,97],"speech":[62,71],"models.":[63],"Using":[64],"Mel":[65],"bank":[66],"log-energy":[67],"features,":[68],"classical":[69],"HMMs":[72],"were":[73,119,130],"replaced":[74],"models":[76],"which":[78],"model":[80,117,134],"components":[81,118],"corresponding":[82],"low":[84],"energy":[85],"are":[86],"not":[87],"considered":[88],"during":[89],"recognition.":[90],"Application":[91],"matched":[98],"showed":[100],"recognition":[102],"performance":[103,128],"was":[104],"equal":[105],"or":[106],"better":[107],"compared":[108],"baseline":[110],"when":[111],"less":[112],"than":[113],"45%":[114],"discarded.":[120],"case":[123],"noisy":[125],"data,":[126],"gains":[129],"marginal":[131],"component":[135],"selections":[136],"studied":[137],"so":[138],"far.":[139],"Analysis":[140],"results":[143],"suggests":[144],"future":[146],"research":[147],"should":[148],"focus":[149],"combining":[151],"model-driven":[154],"approach":[155],"with":[156],"data-driven":[157],"methods.":[158]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}