{"id":"https://openalex.org/W2065927558","doi":"https://doi.org/10.1109/asru.2013.6707760","title":"Acoustic unit discovery and pronunciation generation from a grapheme-based lexicon","display_name":"Acoustic unit discovery and pronunciation generation from a grapheme-based lexicon","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2065927558","doi":"https://doi.org/10.1109/asru.2013.6707760","mag":"2065927558"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},"type":"preprint","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/A5047770365","display_name":"William M. Hartmann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"William Hartmann","raw_affiliation_strings":["Spoken Language Processing Group, CNRS, Orsay, France","Spoken Language Process. Group, LIMSI, Orsay, France"],"affiliations":[{"raw_affiliation_string":"Spoken Language Processing Group, CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI, Orsay, France","institution_ids":["https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004126","display_name":"Anindya Roy","orcid":"https://orcid.org/0000-0002-0583-2661"},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anindya Roy","raw_affiliation_strings":["Spoken Language Processing Group, CNRS, Orsay, France","Spoken Language Process. Group, LIMSI, Orsay, France"],"affiliations":[{"raw_affiliation_string":"Spoken Language Processing Group, CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI, Orsay, France","institution_ids":["https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062446882","display_name":"Lori Lamel","orcid":"https://orcid.org/0000-0001-7443-9938"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lori Lamel","raw_affiliation_strings":["Spoken Language Processing Group, CNRS, Orsay, France","Spoken Language Process. Group, LIMSI, Orsay, France"],"affiliations":[{"raw_affiliation_string":"Spoken Language Processing Group, CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI, Orsay, France","institution_ids":["https://openalex.org/I4210115485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109214406","display_name":"Jean\u2010Luc Gauvain","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Luc Gauvain","raw_affiliation_strings":["Spoken Language Processing Group, CNRS, Orsay, France","Spoken Language Process. Group, LIMSI, Orsay, France"],"affiliations":[{"raw_affiliation_string":"Spoken Language Processing Group, CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI, Orsay, France","institution_ids":["https://openalex.org/I4210115485"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047770365"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"],"apc_list":null,"apc_paid":null,"fwci":3.5372,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93127703,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"380","last_page":"385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.8782955408096313},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7999410629272461},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.7698186635971069},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7288722991943359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6621112823486328},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6199740171432495},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5313926935195923},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.49977755546569824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.472896009683609},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4405863285064697},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.437730073928833},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4318724274635315},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42144906520843506},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4118630588054657},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10625597834587097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8782955408096313},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7999410629272461},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.7698186635971069},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7288722991943359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6621112823486328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6199740171432495},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5313926935195923},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.49977755546569824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.472896009683609},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4405863285064697},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.437730073928833},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4318724274635315},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42144906520843506},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4118630588054657},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10625597834587097},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru.2013.6707760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.700.9619","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.700.9619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.betweenzeroandone.com/publications/hartmann_asru2013.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01843433v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01843433","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Automatic Speech Recognition and Understanding Workshop, Dec 2013, Olomouc, Czech Republic. ⟨10.1109/ASRU.2013.6707760⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W189099732","https://openalex.org/W1510837697","https://openalex.org/W1513168562","https://openalex.org/W1608231129","https://openalex.org/W1964917299","https://openalex.org/W2035611878","https://openalex.org/W2047497400","https://openalex.org/W2090755665","https://openalex.org/W2096854399","https://openalex.org/W2100768664","https://openalex.org/W2117041980","https://openalex.org/W2124807415","https://openalex.org/W2132914434","https://openalex.org/W2136251587","https://openalex.org/W2165874743","https://openalex.org/W2401464865","https://openalex.org/W3150637114","https://openalex.org/W6630740198","https://openalex.org/W6675022971","https://openalex.org/W6679880043","https://openalex.org/W6684578312"],"related_works":["https://openalex.org/W2080578089","https://openalex.org/W2384400852","https://openalex.org/W3204898214","https://openalex.org/W2963259630","https://openalex.org/W4240926580","https://openalex.org/W2070920720","https://openalex.org/W2398549619","https://openalex.org/W1542743110","https://openalex.org/W2179005426","https://openalex.org/W2463396630"],"abstract_inverted_index":{"We":[0,76],"present":[1],"a":[2,34,40,53,62,72,78,106,116],"framework":[3],"for":[4,81],"discovering":[5],"acoustic":[6,44],"units":[7],"and":[8],"generating":[9],"an":[10,15,97],"associated":[11],"pronunciation":[12,50],"lexicon":[13,51],"from":[14,61],"initial":[16],"grapheme-based":[17,118],"recognition":[18],"system.":[19,119],"Our":[20,120],"approach":[21,37,121],"consists":[22],"of":[23,42,64,91],"two":[24],"distinct":[25],"contributions.":[26],"First,":[27],"context-dependent":[28],"grapheme":[29],"models":[30],"are":[31,68],"clustered":[32],"using":[33,52],"spectral":[35],"clustering":[36],"to":[38,70,115,126],"create":[39,71],"set":[41,67],"phone-like":[43],"units.":[45],"Next,":[46],"we":[47],"transform":[48],"the":[49,65,83,89,92,102,135],"statistical":[54],"machine":[55],"translation-based":[56],"approach.":[57],"Pronunciation":[58],"hypotheses":[59],"generated":[60],"decoding":[63],"training":[66],"used":[69],"phrase-based":[73,84],"translation":[74],"table.":[75],"propose":[77],"novel":[79],"method":[80],"scoring":[82],"rules":[85],"that":[86],"significantly":[87],"improves":[88],"output":[90],"transformation":[93],"process.":[94],"Results":[95],"on":[96],"English":[98],"language":[99],"dataset":[100],"demonstrate":[101],"combined":[103],"methods":[104],"provide":[105],"13%":[107],"relative":[108],"reduction":[109],"in":[110,134],"word":[111],"error":[112],"rate":[113],"compared":[114],"baseline":[117],"could":[122],"potentially":[123],"be":[124],"applied":[125],"low-resource":[127],"languages":[128],"without":[129],"existing":[130],"lexicons,":[131],"such":[132],"as":[133],"Babel":[136],"project.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}