{"id":"https://openalex.org/W2128542418","doi":"https://doi.org/10.1109/icassp.2004.1326655","title":"Speech transcription in multiple languages","display_name":"Speech transcription in multiple languages","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2128542418","doi":"https://doi.org/10.1109/icassp.2004.1326655","mag":"2128542418"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5062446882","display_name":"Lori Lamel","orcid":"https://orcid.org/0000-0001-7443-9938"},"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":"L. Lamel","raw_affiliation_strings":["LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","Spoken Language Process. Group, LIMSI-CNRS, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109050158","display_name":"J.-L. Gauvain","orcid":null},"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":"J.L. Gauvain","raw_affiliation_strings":["LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","Spoken Language Process. Group, LIMSI-CNRS, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021094021","display_name":"Gilles Adda","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":"G. Adda","raw_affiliation_strings":["LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","Spoken Language Process. Group, LIMSI-CNRS, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041761844","display_name":"Martine Adda\u2010Decker","orcid":"https://orcid.org/0000-0003-2154-7438"},"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":"M. Adda-Decker","raw_affiliation_strings":["LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","Spoken Language Process. Group, LIMSI-CNRS, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081571204","display_name":"L. Canseco","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":"L. Canseco","raw_affiliation_strings":["LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","Spoken Language Process. Group, LIMSI-CNRS, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113334610","display_name":"L. Chen","orcid":null},"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":"L. Chen","raw_affiliation_strings":["LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","Spoken Language Process. Group, LIMSI-CNRS, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088375891","display_name":"Olivier Galibert","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":"O. Galibert","raw_affiliation_strings":["LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","Spoken Language Process. Group, LIMSI-CNRS, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108517024","display_name":"Abdelkhalek Messaoudi","orcid":null},"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":"A. Messaoudi","raw_affiliation_strings":["LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","Spoken Language Process. Group, LIMSI-CNRS, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015857371","display_name":"Holger Schwenk","orcid":null},"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":"H. Schwenk","raw_affiliation_strings":["LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","Spoken Language Process. Group, LIMSI-CNRS, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Spoken Language Processing Group, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5062446882"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"],"apc_list":null,"apc_paid":null,"fwci":2.3127,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89871441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"iii","last_page":"757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.993399977684021,"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":0.867605447769165},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7513562440872192},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6409651041030884},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6237978935241699},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47344183921813965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4628872573375702},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3205973505973816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.867605447769165},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7513562440872192},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6409651041030884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6237978935241699},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47344183921813965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4628872573375702},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3205973505973816},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01434483v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01434483","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":"International Conference on Acoustics, Speech, and Signal Processing, May 2004, Montr\u00e9al, Canada. pp.753--756, ⟨10.1109/ICASSP.2004.1326655⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W112233275","https://openalex.org/W1555037511","https://openalex.org/W1741269295","https://openalex.org/W1975113979","https://openalex.org/W1975532813","https://openalex.org/W2016243284","https://openalex.org/W2033436836","https://openalex.org/W2103127925","https://openalex.org/W2119335056","https://openalex.org/W2479240035","https://openalex.org/W2914008274","https://openalex.org/W6604590616","https://openalex.org/W6871885761"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2917843404","https://openalex.org/W3114261385","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"The":[0,14],"paper":[1],"summarizes":[2],"recent":[3],"work":[4,68],"underway":[5],"at":[6,119],"LIMSI":[7],"on":[8,55,61,69],"speech-to-text":[9],"transcription":[10,33,107],"in":[11,50,127],"multiple":[12],"languages.":[13],"research":[15],"has":[16,58],"been":[17,36],"oriented":[18],"towards":[19],"the":[20,51,62,80,83,92,98,101,110,124,140],"processing":[21,75],"of":[22,82,97,103,139],"broadcast":[23],"audio":[24,84],"and":[25,41,72,100,137,145],"conversational":[26,56],"speech":[27,57],"for":[28,38,108],"information":[29,111],"access.":[30],"Broadcast":[31],"news":[32],"systems":[34],"have":[35],"developed":[37],"seven":[39],"languages,":[40,136],"it":[42],"is":[43],"planned":[44],"to":[45,89,134],"address":[46],"several":[47],"other":[48,135],"languages":[49],"near":[52],"term.":[53],"Research":[54],"mainly":[59],"focused":[60],"English":[63],"language,":[64],"with":[65,91],"some":[66],"initial":[67],"French,":[70],"Arabic":[71],"Spanish.":[73],"Automatic":[74],"must":[76],"take":[77],"into":[78],"account":[79],"characteristics":[81],"data,":[85],"such":[86],"as":[87],"needing":[88],"deal":[90],"continuous":[93],"data":[94],"stream,":[95],"specificities":[96,142],"language":[99,129,141],"use":[102],"an":[104],"imperfect":[105],"word":[106,121],"accessing":[109],"content.":[112],"Our":[113],"experience":[114],"thus":[115],"far":[116],"indicates":[117],"that":[118],"today's":[120],"error":[122],"rates,":[123],"techniques":[125],"used":[126],"one":[128],"can":[130],"be":[131],"successfully":[132],"ported":[133],"most":[138],"concern":[143],"lexical":[144],"pronunciation":[146],"modeling.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}