{"id":"https://openalex.org/W56231661","doi":"https://doi.org/10.21437/interspeech.2004-253","title":"Automated lexical adaptation and speaker clustering based on pronunciation habits for non-native speech recognition","display_name":"Automated lexical adaptation and speaker clustering based on pronunciation habits for non-native speech recognition","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W56231661","doi":"https://doi.org/10.21437/interspeech.2004-253","mag":"56231661"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-253","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"article","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/A5045093641","display_name":"Antoine Raux","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Antoine Raux","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5045093641"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.3127,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88835439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"613","last_page":"616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9959999918937683,"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":0.830720067024231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7217060327529907},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6962677836418152},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6756185293197632},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6373017430305481},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5819734930992126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5522933006286621},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5294522643089294},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5221967101097107},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5092984437942505},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.44447270035743713},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.20884281396865845},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12972798943519592},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.05862674117088318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.830720067024231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7217060327529907},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6962677836418152},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6756185293197632},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6373017430305481},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5819734930992126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5522933006286621},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5294522643089294},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5221967101097107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5092984437942505},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.44447270035743713},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.20884281396865845},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12972798943519592},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.05862674117088318},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2004-253","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.470.2926","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.470.2926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mirlab.org/conference_papers/International_Conference/ICSLP 2004/contents/TuC_pdf/TuC2105o/TuC2105o.6_p1212.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.6193","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.6193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~antoine/papers/icslp2004b.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W254474377","https://openalex.org/W1496781369","https://openalex.org/W1992155534","https://openalex.org/W2013196554"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2529301793","https://openalex.org/W2350724007","https://openalex.org/W2384121599","https://openalex.org/W2355751417","https://openalex.org/W2038083449","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,13,40,73,95],"method":[4],"to":[5,52,67],"improve":[6],"speech":[7,11],"recog-nition":[8],"for":[9,78],"non-native":[10],"in":[12,33,59],"spoken":[14],"dialogue":[15],"system.":[16],"Based":[17],"on":[18,39,86],"very":[19],"general":[20],"rules":[21],"about":[22],"possible":[23],"vocalic":[24],"sub-stitutions,":[25],"the":[26,53,56,60,110,115],"frequency":[27],"of":[28,30,43,55],"occurrence":[29],"each":[31,79,87,119],"substitu-tion":[32],"different":[34],"phonetic":[35,70],"contexts":[36],"is":[37,76,83],"estimated":[38],"small":[41],"set":[42,62],"recordings.":[44],"The":[45],"most":[46],"frequently":[47],"observed":[48],"substitu-tions":[49],"are":[50,63],"applied":[51],"lexicon":[54],"recognizer.":[57],"Speak-ers":[58],"training":[61],"automatically":[64],"clustered":[65],"accord-ing":[66],"their":[68],"preferred":[69],"variants,":[71],"and":[72],"specific":[74],"lex-icon":[75],"built":[77],"cluster.":[80,88],"Acoustic":[81],"adaptation":[82,93,101],"also":[84],"performed":[85],"Experiments":[89],"show":[90],"that":[91],"lexical":[92],"provides":[94],"relative":[96],"WER":[97,108],"reduction":[98],"over":[99],"acoustic":[100],"alone.":[102],"Lexical":[103],"clustering":[104],"can":[105,112],"further":[106],"reduce":[107],"if":[109],"system":[111],"reliably":[113],"select":[114],"cluster":[116],"best":[117],"matching":[118],"input":[120],"utterance.":[121],"1.":[122]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}