{"id":"https://openalex.org/W215171336","doi":"https://doi.org/10.21437/interspeech.2006-28","title":"Multilingual non-native speech recognition using phonetic confusion-based acoustic model modification and graphemic constraints","display_name":"Multilingual non-native speech recognition using phonetic confusion-based acoustic model modification and graphemic constraints","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W215171336","doi":"https://doi.org/10.21437/interspeech.2006-28","mag":"215171336"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-28","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-28","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00110496","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068303736","display_name":"Ghazi Bouselmi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"G. Bouselmi","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046546502","display_name":"Dominique Fohr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Fohr","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073463405","display_name":"Irina Illina","orcid":"https://orcid.org/0000-0003-2598-4643"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"I. Illina","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111403479","display_name":"Jean-Paul Haton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Paul Haton","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068303736"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5825,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95348622,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"paper 1569","last_page":"Mon1BuP.2"},"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/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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":0.779403805732727},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.7176030278205872},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6885855793952942},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6471375226974487},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6302705407142639},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5610776543617249},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5200707316398621},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.49968528747558594},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.47692033648490906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47393709421157837},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44833239912986755},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4199792146682739},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.4176328182220459},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.347321093082428},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3359307646751404},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2953891158103943},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09609410166740417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779403805732727},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.7176030278205872},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6885855793952942},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6471375226974487},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6302705407142639},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5610776543617249},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5200707316398621},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.49968528747558594},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.47692033648490906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47393709421157837},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44833239912986755},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4199792146682739},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.4176328182220459},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.347321093082428},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3359307646751404},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2953891158103943},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09609410166740417},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2006-28","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-28","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:inria-00110496v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00110496","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Ninth International Conference on Spoken Language Processing - ICSLP 2006, Sep 2006, Pittsburgh, PA/USA","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00110496v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00110496","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Ninth International Conference on Spoken Language Processing - ICSLP 2006, Sep 2006, Pittsburgh, PA/USA","raw_type":"Conference papers"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1544284505","https://openalex.org/W1556910286","https://openalex.org/W1783786615","https://openalex.org/W2150699467","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4366957107","https://openalex.org/W2096389830","https://openalex.org/W1499383998","https://openalex.org/W4298261218","https://openalex.org/W2132474591","https://openalex.org/W2250825451","https://openalex.org/W3151376046","https://openalex.org/W430347950","https://openalex.org/W2992378684","https://openalex.org/W2105439218"],"abstract_inverted_index":{"In":[0,106,124],"this":[1,125],"paper":[2],"we":[3,94],"present":[4],"an":[5],"automated":[6],"approach":[7,146],"for":[8,43],"non-native":[9,40,84,153],"speech":[10,41,154],"recognition.":[11],"We":[12,143],"introduce":[13],"a":[14,39,44],"new":[15],"phonetic":[16,102,128],"confusion":[17,33,103,129],"concept":[18],"that":[19,83],"associates":[20],"sequences":[21,139],"of":[22,66,73,91,121,134,140],"native":[23],"language":[24,29,158],"(NL)":[25],"phones":[26,75,110],"to":[27,60,77,116,171,181],"spoken":[28,157],"(SL)":[30],"phones.":[31,142],"Phonetic":[32],"rules":[34,57],"are":[35,58,114],"automatically":[36],"extracted":[37],"from":[38,169,179],"database":[42],"given":[45],"NL":[46,141],"and":[47,52,138,151,178],"SL":[48],"using":[49],"both":[50],"NL's":[51,74],"SL's":[53,67],"ASR":[54,68,163],"systems.":[55],"These":[56],"used":[59,97],"modify":[61],"the":[62,89,92,101,107,109,117,122,127],"acoustic":[63,71],"models":[64,72],"(HMMs)":[65],"by":[69],"adding":[70],"according":[76],"these":[78],"rules.":[79],"As":[80],"pronunciation":[81],"errors":[82],"speakers":[85],"produce":[86],"depend":[87],"on":[88,147],"writing":[90],"words,":[93],"have":[95],"also":[96],"graphemic":[98],"constraints":[99],"in":[100,111,174,183],"extraction":[104],"process.":[105],"lexicon,":[108],"words'":[112],"pronunciations":[113],"linked":[115],"corresponding":[118],"graphemes":[119],"(characters)":[120],"word.":[123],"way,":[126],"is":[130,159],"established":[131],"between":[132],"couples":[133],"(SL":[135],"phones,":[136],"graphemes)":[137],"evaluated":[144],"our":[145],"French,":[148],"Italian,":[149],"Spanish":[150],"Greek":[152],"databases.":[155],"The":[156,161],"English.":[160],"modified":[162],"system":[164],"achieved":[165],"significant":[166],"improvements":[167],"ranging":[168],"20.3%":[170],"43.2%":[172],"(relative)":[173],"sentence":[175],"error":[176],"rate":[177],"26.6%":[180],"50.0%":[182],"WER.":[184]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}