{"id":"https://openalex.org/W21963070","doi":"https://doi.org/10.21437/interspeech.2009-350","title":"A comparison of audio-free speech recognition error prediction methods","display_name":"A comparison of audio-free speech recognition error prediction methods","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W21963070","doi":"https://doi.org/10.21437/interspeech.2009-350","mag":"21963070"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-350","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-350","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/A5036738038","display_name":"Preethi Jyothi","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Preethi Jyothi","raw_affiliation_strings":["The Ohio State University, Columbus, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, United States","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["The Ohio State University, Columbus, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, United States","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1211","last_page":"1214"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/T12031","display_name":"Speech and dialogue systems","score":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.8128643035888672},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7570143938064575},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.608300507068634},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5520926117897034},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5343325138092041},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5244272351264954},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5214011669158936},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.515995979309082},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49519529938697815},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.47998520731925964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4752209782600403},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.45236533880233765},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.449362188577652},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44342249631881714},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4110684096813202},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4104742407798767},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3511141836643219},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2830701470375061},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09399667382240295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8128643035888672},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7570143938064575},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.608300507068634},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5520926117897034},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5343325138092041},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5244272351264954},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5214011669158936},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.515995979309082},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49519529938697815},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.47998520731925964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4752209782600403},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.45236533880233765},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.449362188577652},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44342249631881714},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4110684096813202},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4104742407798767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3511141836643219},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2830701470375061},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09399667382240295},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-350","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-350","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":[{"display_name":"Quality Education","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W174066529","https://openalex.org/W222076935","https://openalex.org/W1949738355","https://openalex.org/W1980280616","https://openalex.org/W1993607814","https://openalex.org/W2141141395","https://openalex.org/W2144462324"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W2145230572","https://openalex.org/W2166312020","https://openalex.org/W2620660273","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W4401751953","https://openalex.org/W2619911963","https://openalex.org/W4385611764"],"abstract_inverted_index":{"Predicting":[0],"possible":[1],"speech":[2],"recognition":[3,44,76],"errors":[4,45,104],"can":[5,79],"be":[6],"invaluable":[7],"for":[8,29,62],"a":[9,22,34,95],"number":[10,102],"of":[11,39,83,92,99,103],"Automatic":[12,126],"Speech":[13,127],"Recognition":[14],"(ASR)":[15],"applications.":[16],"In":[17],"this":[18],"study,":[19],"we":[20,78],"extend":[21],"Weighted":[23],"Finite":[24,123],"State":[25,124],"Transducer":[26],"(WFST)":[27],"framework":[28,70],"error":[30],"prediction":[31,64,130],"to":[32,50,71,115],"facilitate":[33],"comparison":[35],"between":[36,57],"two":[37],"approaches":[38],"predicting":[40],"confusable":[41],"words:":[42],"examining":[43],"on":[46],"the":[47,58,63,69,84,100,106,116],"training":[48],"set":[49],"learn":[51],"phone":[52],"confusions":[53],"and":[54,77,94],"utilizing":[55],"distances":[56],"phonetic":[59],"acoustic":[60,112],"models":[61],"task.":[65],"We":[66],"also":[67],"expand":[68],"deal":[72],"with":[73],"continuous":[74],"word":[75],"accurately":[80],"predict":[81],"60%":[82],"misrecognized":[85],"sentences":[86],"(with":[87],"an":[88],"average":[89],"words-per-sentence":[90],"count":[91],"15)":[93],"little":[96],"over":[97],"70%":[98],"total":[101],"from":[105],"unseen":[107],"test":[108,117],"data":[109,118],"where":[110],"no":[111],"information":[113],"related":[114],"is":[119],"utilized.":[120],"Index":[121],"Terms:":[122],"Transducer,":[125],"Recognition,":[128],"Error":[129]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}