{"id":"https://openalex.org/W1847682101","doi":"https://doi.org/10.21437/interspeech.2007-126","title":"Modelling confusion matrices to improve speech recognition accuracy, with an application to dysarthric speech","display_name":"Modelling confusion matrices to improve speech recognition accuracy, with an application to dysarthric speech","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W1847682101","doi":"https://doi.org/10.21437/interspeech.2007-126","mag":"1847682101"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-126","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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":[{"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":"Omar Caballero Morales","raw_affiliation_strings":["#N#University of East Anglia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#University of East Anglia","institution_ids":["https://openalex.org/I1118541"]}]},{"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 Cox","raw_affiliation_strings":["#N#University of East Anglia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#University of East Anglia","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1118541"],"apc_list":null,"apc_paid":null,"fwci":0.8903,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.72237713,"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":"1565","last_page":"1568"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.8440424203872681},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7824870347976685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7106045484542847},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.4465845227241516},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43540704250335693},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38555020093917847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3458324670791626},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10853466391563416}],"concepts":[{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.8440424203872681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7824870347976685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7106045484542847},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.4465845227241516},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43540704250335693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38555020093917847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3458324670791626},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10853466391563416},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2007-126","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1932968309","https://openalex.org/W2118379083","https://openalex.org/W2130169233","https://openalex.org/W2140360678"],"related_works":["https://openalex.org/W4366202965","https://openalex.org/W2349679704","https://openalex.org/W2570625548","https://openalex.org/W3154844368","https://openalex.org/W2981428355","https://openalex.org/W2150288981","https://openalex.org/W1599055764","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Dysarthria":[0],"is":[1,96],"a":[2,48,88],"motor":[3],"speech":[4,21,40],"disorder":[5],"characterized":[6],"by":[7,60],"weakness,":[8],"paralysis,":[9],"or":[10,94],"poor":[11],"coordination":[12],"of":[13,66,84,105],"the":[14,67,82],"muscles":[15],"responsible":[16],"for":[17,28,90,102],"speech.":[18],"Although":[19],"automatic":[20],"recognition":[22,41,53],"(ASR)":[23],"systems":[24],"have":[25],"been":[26],"developed":[27],"disordered":[29],"speech,":[30],"factors":[31],"such":[32],"as":[33],"low":[34,58],"intelligibility":[35,59],"and":[36,98],"limited":[37],"vocabulary":[38],"decrease":[39],"accuracy.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"introduce":[47],"technique":[49,73],"that":[50],"can":[51],"increase":[52],"accuracy":[54],"in":[55],"speakers":[56],"with":[57],"incorporating":[61],"information":[62],"from":[63,87],"an":[64],"estimate":[65],"speaker's":[68],"phoneme":[69],"confusion":[70,91],"matrix.":[71],"The":[72],"performs":[74],"much":[75],"better":[76],"than":[77],"standard":[78],"speaker":[79,89],"adaptation":[80,95],"when":[81],"number":[83],"sentences":[85],"available":[86],"matrix":[92],"estimation":[93],"low,":[97],"has":[99],"similar":[100],"performance":[101],"larger":[103],"numbers":[104],"sentences.":[106]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"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"}