{"id":"https://openalex.org/W2168391696","doi":"https://doi.org/10.1109/icassp.2012.6288998","title":"Evaluating grapheme-to-phoneme converters in automatic speech recognition context","display_name":"Evaluating grapheme-to-phoneme converters in automatic speech recognition context","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2168391696","doi":"https://doi.org/10.1109/icassp.2012.6288998","mag":"2168391696"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00753364","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030903462","display_name":"Denis Jouvet","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4210127166","display_name":"Centre Inria de l'Universit\u00e9 de Lorraine","ror":"https://ror.org/03fcjvn64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Denis Jouvet","raw_affiliation_strings":["Speech Group, INRIA-LORIA, Villers-les-Nancy, France","Analysis, perception and recognition of speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Group, INRIA-LORIA, Villers-les-Nancy, France","institution_ids":["https://openalex.org/I4210127166","https://openalex.org/I1326498283","https://openalex.org/I4210121838"]},{"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":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4210127166","display_name":"Centre Inria de l'Universit\u00e9 de Lorraine","ror":"https://ror.org/03fcjvn64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dominique Fohr","raw_affiliation_strings":["Speech Group, INRIA-LORIA, Villers-les-Nancy, France","Analysis, perception and recognition of speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Group, INRIA-LORIA, Villers-les-Nancy, France","institution_ids":["https://openalex.org/I4210127166","https://openalex.org/I1326498283","https://openalex.org/I4210121838"]},{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073463405","display_name":"Irina Illina","orcid":"https://orcid.org/0000-0003-2598-4643"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4210127166","display_name":"Centre Inria de l'Universit\u00e9 de Lorraine","ror":"https://ror.org/03fcjvn64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Irina Illina","raw_affiliation_strings":["Speech Group, INRIA-LORIA, Villers-les-Nancy, France","Analysis, perception and recognition of speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Group, INRIA-LORIA, Villers-les-Nancy, France","institution_ids":["https://openalex.org/I4210127166","https://openalex.org/I1326498283","https://openalex.org/I4210121838"]},{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4228,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94582888,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"42","issue":null,"first_page":"4821","last_page":"4824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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/pronunciation","display_name":"Pronunciation","score":0.9065564870834351},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.8236465454101562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7792888879776001},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7148710489273071},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.679874837398529},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6020969748497009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5102136135101318},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.448933482170105},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.42917680740356445},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4033857583999634},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0929608941078186},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0764051079750061},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06464084982872009}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9065564870834351},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.8236465454101562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792888879776001},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7148710489273071},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.679874837398529},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6020969748497009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5102136135101318},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.448933482170105},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.42917680740356445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4033857583999634},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0929608941078186},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0764051079750061},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06464084982872009},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00753364v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00753364","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":"ICASSP - 2012 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar 2012, Kyoto, Japan. pp.4821 - 4824, ⟨10.1109/ICASSP.2012.6288998⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00753364v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00753364","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":"ICASSP - 2012 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar 2012, Kyoto, Japan. pp.4821 - 4824, ⟨10.1109/ICASSP.2012.6288998⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W49690127","https://openalex.org/W163811496","https://openalex.org/W177378321","https://openalex.org/W189099732","https://openalex.org/W201187342","https://openalex.org/W2016717966","https://openalex.org/W2066892873","https://openalex.org/W2090755665","https://openalex.org/W2097497389","https://openalex.org/W2209189647","https://openalex.org/W2396216106","https://openalex.org/W2609704091","https://openalex.org/W4285719527","https://openalex.org/W6602028794","https://openalex.org/W6607658528","https://openalex.org/W6607997220","https://openalex.org/W6688431300","https://openalex.org/W6711951891"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W4391124013","https://openalex.org/W2080578089","https://openalex.org/W4387715848","https://openalex.org/W2179005426"],"abstract_inverted_index":{"This":[0],"paper":[1,69],"deals":[2],"with":[3],"the":[4,26,29,46,51,65,79,87,97,107,130,141,145],"evaluation":[5],"of":[6,25,28,48,50,67,144],"grapheme-to-phoneme":[7],"(G2P)":[8],"converters":[9],"in":[10,71,96,106],"a":[11,60,73],"speech":[12,61,74,111],"recognition":[13,62,75,112],"context.":[14],"The":[15,83],"precision":[16],"and":[17,129],"recall":[18],"rates":[19],"are":[20,37,56,104,115],"investigated":[21],"as":[22,136,138],"potential":[23],"measures":[24],"quality":[27],"multiple":[30],"generated":[31],"pronunciation":[32,81,98,101,142],"variants.":[33,82],"Very":[34],"different":[35,120],"results":[36,84],"obtained":[38],"whether":[39],"or":[40],"not":[41],"we":[42],"take":[43],"into":[44],"account":[45],"frequency":[47],"occurrence":[49],"words.":[52,148],"Since":[53],"G2P":[54,80,121],"systems":[55],"rarely":[57],"evaluated":[58],"on":[59,125,132],"performance":[63,113],"basis,":[64],"originality":[66],"this":[68],"consists":[70],"using":[72],"system":[76],"to":[77,93],"evaluate":[78],"show":[85],"that":[86],"training":[88],"process":[89],"is":[90],"quite":[91],"robust":[92],"some":[94],"errors":[95,103],"lexicon,":[99],"whereas":[100],"lexicon":[102],"harmful":[105],"decoding":[108],"process.":[109],"Noticeable":[110],"improvements":[114],"achieved":[116],"by":[117,139],"combining":[118],"two":[119],"converters,":[122],"one":[123],"based":[124],"conditional":[126],"random":[127],"fields":[128],"other":[131],"joint":[133],"multigram":[134],"models,":[135],"well":[137],"checking":[140],"variants":[143],"most":[146],"frequent":[147]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}