{"id":"https://openalex.org/W2150638823","doi":"https://doi.org/10.1109/icassp.2002.5743654","title":"Accounting for uncertainity in observations: A new paradigm for Robust Automatic Speech Recognition","display_name":"Accounting for uncertainity in observations: A new paradigm for Robust Automatic Speech Recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2150638823","doi":"https://doi.org/10.1109/icassp.2002.5743654","mag":"2150638823"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743654","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5075577786","display_name":"Trausti Kristjansson","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Trausti T. Kristjansson","raw_affiliation_strings":["Probabilistic and Statistical Inference Group, University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Probabilistic and Statistical Inference Group, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003361977","display_name":"Brendan J. Frey","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brendan J. Frey","raw_affiliation_strings":["Probabilistic and Statistical Inference Group, University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Probabilistic and Statistical Inference Group, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075577786"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":1.9786,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.86142002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"61"},"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":0.9995999932289124,"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":0.9987999796867371,"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":0.7566395401954651},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6580675840377808},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6200448274612427},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5766416192054749},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5162877440452576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4349752366542816},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3485632836818695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3268626928329468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566395401954651},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6580675840377808},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6200448274612427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5766416192054749},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5162877440452576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4349752366542816},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3485632836818695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3268626928329468},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5743654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743654","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.15.9753","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.15.9753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://newgist.uwaterloo.ca/~trausti/Papers/kristjansson2002icassp.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W36799504","https://openalex.org/W105750483","https://openalex.org/W174003511","https://openalex.org/W1573570773","https://openalex.org/W1864449204","https://openalex.org/W2099111195"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2766405861","https://openalex.org/W2360975119","https://openalex.org/W2912421143","https://openalex.org/W2372487155"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2],"new":[3,42],"paradigm":[4,43],"for":[5],"Robust":[6],"Automatic":[7],"Speech":[8],"Recognition":[9],"that":[10,122],"directly":[11],"incorporates":[12],"information":[13,65],"about":[14,66],"the":[15,24,32,39,41,45,50,58,67,72,90,96,99,110,132],"uncertainty":[16,70],"introduced":[17,88],"by":[18,89,95],"environmental":[19],"noise.":[20],"In":[21],"contrast":[22],"to":[23,56,81,108],"feature":[25],"cleaning":[26],"and":[27,49,85],"model":[28,82],"adaptation":[29],"paradigms,":[30],"where":[31],"noise":[33,46,84,91,100],"compensation":[34,47],"mechanism":[35,48],"is":[36,93],"separate":[37],"from":[38],"recognizer,":[40],"unifies":[44],"recognizer.":[51],"The":[52,74,102],"Algonquin":[53,75,103],"framework":[54,76,104],"serves":[55],"demonstrate":[57],"importance":[59],"of":[60,69,98,112,134],"retaining":[61,113],"soft":[62,116,135],"information,":[63],"i.e.":[64],"degree":[68],"in":[71,125],"observations.":[73],"employs":[77],"Gaussian":[78],"mixture":[79],"models":[80],"both":[83],"speech.":[86],"Uncertainty":[87],"process":[92],"captured":[94],"variance":[97],"model.":[101],"also":[105],"allows":[106],"us":[107],"isolate":[109],"effect":[111],"or":[114],"discarding":[115],"information.":[117,136],"Our":[118],"initial":[119],"results":[120],"indicate":[121],"substantial":[123],"improvements":[124],"recognition":[126],"rates":[127],"can":[128],"be":[129],"achieved":[130],"through":[131],"use":[133]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}