{"id":"https://openalex.org/W1506349653","doi":"https://doi.org/10.21437/interspeech.2009-207","title":"On the estimation and the use of confusion-matrices for improving ASR accuracy","display_name":"On the estimation and the use of confusion-matrices for improving ASR accuracy","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W1506349653","doi":"https://doi.org/10.21437/interspeech.2009-207","mag":"1506349653"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-207","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5058717726","display_name":"Omar Caballero Morales","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omar Caballero Morales","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101798651","display_name":"Stephen Cox","orcid":"https://orcid.org/0000-0002-4443-1000"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stephen J. Cox","raw_affiliation_strings":["University of East Anglia, Norwich, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of East Anglia, Norwich, United Kingdom","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4874,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.57182379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1599","last_page":"1602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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/confusion","display_name":"Confusion","score":0.8249684572219849},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.8012810945510864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7353559136390686},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7250689268112183},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6812552213668823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6455154418945312},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5354927182197571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5088098645210266},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5054275989532471},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4628976881504059},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3442632257938385},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0604594349861145}],"concepts":[{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.8249684572219849},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.8012810945510864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353559136390686},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7250689268112183},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6812552213668823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6455154418945312},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5354927182197571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088098645210266},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5054275989532471},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4628976881504059},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3442632257938385},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0604594349861145},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-207","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W126654485","https://openalex.org/W1847682101","https://openalex.org/W1902027874","https://openalex.org/W2133446705","https://openalex.org/W2140360678","https://openalex.org/W2146871184","https://openalex.org/W3143596294"],"related_works":["https://openalex.org/W4390394189","https://openalex.org/W4366202965","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W1969293528"],"abstract_inverted_index":{"In":[0,51],"previous":[1,76],"work,":[2],"we":[3,54],"described":[4],"how":[5],"learning":[6],"the":[7,35,61,81,111,121],"pattern":[8],"of":[9,83,88],"recognition":[10,24,131],"errors":[11],"made":[12,104],"by":[13,90],"an":[14,56],"individual":[15],"using":[16,91,105,114],"a":[17,28,115],"certain":[18],"ASR":[19,112],"system":[20],"leads":[21],"to":[22,96,135],"increased":[23],"accuracy":[25,132],"compared":[26],"with":[27,40],"standard":[29],"MLLR":[30],"adaptation":[31],"approach.":[32],"This":[33],"was":[34,46],"case":[36],"for":[37,48,59,64,67],"low-intelligibility":[38],"speakers":[39,69],"dysarthric":[41],"speech,":[42],"but":[43],"no":[44],"improvement":[45],"observed":[47],"normal":[49,68,136],"speakers.":[50],"this":[52],"paper,":[53],"describe":[55],"alternative":[57],"method":[58],"obtaining":[60],"training":[62],"data":[63,84],"confusion-matrix":[65,102],"estimation":[66,87],"which":[70],"is":[71],"more":[72],"effective":[73],"than":[74],"our":[75],"technique.":[77],"We":[78],"also":[79],"address":[80],"issue":[82],"sparsity":[85],"in":[86,129],"confusion-matrices":[89],"non-negative":[92],"matrix":[93],"factorization":[94],"(NMF)":[95],"discover":[97],"structure":[98],"within":[99],"them.":[100],"The":[101],"estimates":[103],"these":[106],"techniques":[107],"are":[108],"integrated":[109],"into":[110],"process":[113],"technique":[116],"termed":[117],"as":[118],"metamodels,":[119],"and":[120],"results":[122],"presented":[123],"here":[124],"show":[125],"statistically":[126],"significant":[127],"gains":[128],"word":[130],"when":[133],"applied":[134],"speech.":[137]},"counts_by_year":[{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}