{"id":"https://openalex.org/W1576787462","doi":"https://doi.org/10.21437/eurospeech.2003-325","title":"Estimating speech recognition error rate without acoustic test data","display_name":"Estimating speech recognition error rate without acoustic test data","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W1576787462","doi":"https://doi.org/10.21437/eurospeech.2003-325","mag":"1576787462"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-325","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5108579848","display_name":"Yonggang Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonggang Deng","raw_affiliation_strings":["Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112784012","display_name":"Milind Mahajan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Milind Mahajan","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111957484","display_name":"Alex Acero","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex Acero","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0215,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.75107978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"929","last_page":"932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9977999925613403,"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":0.7967950701713562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7474541664123535},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7320250272750854},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5778096914291382},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5428358316421509},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5257340669631958},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5032266974449158},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4930853545665741},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.47346964478492737},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.465320348739624},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4644029140472412},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.44926708936691284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44736623764038086},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.43692585825920105},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.43278056383132935},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.42459720373153687},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40030378103256226},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3815595507621765},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29218703508377075},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12649193406105042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08966013789176941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967950701713562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7474541664123535},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7320250272750854},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5778096914291382},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5428358316421509},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5257340669631958},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5032266974449158},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4930853545665741},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.47346964478492737},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.465320348739624},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4644029140472412},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.44926708936691284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44736623764038086},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.43692585825920105},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.43278056383132935},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.42459720373153687},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40030378103256226},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3815595507621765},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29218703508377075},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12649193406105042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08966013789176941},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2003-325","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.4214","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.4214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.microsoft.com/pubs/76841/2003-milindm-eurospeech.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W29464808","https://openalex.org/W285442696","https://openalex.org/W2001800583","https://openalex.org/W2102443632","https://openalex.org/W2132780103","https://openalex.org/W2164098806"],"related_works":["https://openalex.org/W2102309991","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2535886977","https://openalex.org/W2133857928","https://openalex.org/W2143297499","https://openalex.org/W2356694334","https://openalex.org/W2991144886","https://openalex.org/W2790444905","https://openalex.org/W1843778016"],"abstract_inverted_index":{"We":[0,112,139],"address":[1],"the":[2,6,32,46,54,66,70,75,80,99,105,136,148],"problem":[3,27],"of":[4,11,34,42,69,87,118,135,144],"estimating":[5,65],"word":[7,71],"error":[8],"rate":[9],"(WER)":[10],"an":[12,25],"automatic":[13],"speech":[14],"recognition":[15],"(ASR)":[16],"system":[17,78,89,149],"without":[18],"using":[19],"acoustic":[20,106],"test":[21,82,151],"data.":[22],"This":[23],"is":[24,29,90],"important":[26],"which":[28,37,95,124],"faced":[30],"by":[31,74,102,132],"designers":[33],"new":[35],"applications":[36],"use":[38,113],"ASR.":[39],"Quick":[40],"estimate":[41],"WER":[43,145],"early":[44],"in":[45],"design":[47],"cycle":[48],"can":[49],"be":[50],"used":[51],"to":[52,97,150],"guide":[53],"decisions":[55],"involving":[56],"dialog":[57],"strategy":[58],"and":[59],"grammar":[60],"design.":[61],"Our":[62],"approach":[63],"involves":[64],"probability":[67],"distribution":[68],"hypotheses":[72],"produced":[73],"underlying":[76],"ASR":[77,103],"given":[79],"text":[81],"corpus.":[83],"A":[84],"critical":[85],"component":[86],"this":[88],"a":[91,109,114],"phonemic":[92,110,128],"confusion":[93,115],"model":[94,116],"seeks":[96],"capture":[98],"errors":[100],"made":[101],"on":[104],"data":[107],"at":[108],"level.":[111],"composed":[117],"probabilistic":[119],"phoneme":[120],"sequence":[121],"conversion":[122],"rules":[123],"are":[125],"learned":[126],"from":[127,153],"transcription":[129],"pairs":[130],"obtained":[131],"leave-one-out":[133],"decoding":[134],"training":[137],"set.":[138],"show":[140],"reasonably":[141],"close":[142],"estimation":[143],"when":[146],"applying":[147],"sets":[152],"different":[154],"domains.":[155],"1.":[156]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}