{"id":"https://openalex.org/W2017440361","doi":"https://doi.org/10.1145/1871840.1871849","title":"Reshaping automatic speech transcripts for robust high-level spoken document analysis","display_name":"Reshaping automatic speech transcripts for robust high-level spoken document analysis","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2017440361","doi":"https://doi.org/10.1145/1871840.1871849","mag":"2017440361"},"language":"en","primary_location":{"id":"doi:10.1145/1871840.1871849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871840.1871849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth workshop on Analytics for noisy unstructured text data","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/A5022589929","display_name":"J Fayolle","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/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Julien Fayolle","raw_affiliation_strings":["INRIA - IRISA, Rennes, France","Inria - IRISA, Rennes, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA - IRISA, Rennes, France","institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Inria - IRISA, Rennes, France#TAB#","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210133778","https://openalex.org/I2802519937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002686446","display_name":"Fabienne Moreau","orcid":null},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I3124938446","display_name":"Universit\u00e9 Rennes 2","ror":"https://ror.org/01m84wm78","country_code":"FR","type":"education","lineage":["https://openalex.org/I3124938446"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabienne Moreau","raw_affiliation_strings":["University Rennes 2 - IRISA, Rennes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Rennes 2 - IRISA, Rennes, France","institution_ids":["https://openalex.org/I3124938446","https://openalex.org/I2802519937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073795682","display_name":"Christian Raymond","orcid":"https://orcid.org/0000-0002-0963-9367"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christian Raymond","raw_affiliation_strings":["INSA - IRISA, Rennes, France","INSA/IRISA, Rennes, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSA - IRISA, Rennes, France","institution_ids":["https://openalex.org/I2802519937"]},{"raw_affiliation_string":"INSA/IRISA, Rennes, France#TAB#","institution_ids":["https://openalex.org/I2802519937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008190208","display_name":"Guillaume Gravier","orcid":"https://orcid.org/0000-0002-2266-5682"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Gravier","raw_affiliation_strings":["CNRS - IRISA, Rennes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS - IRISA, Rennes, France","institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022589929"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I2802519937","https://openalex.org/I4210133778"],"apc_list":null,"apc_paid":null,"fwci":1.8643,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87321695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987999796867371,"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":0.8467147946357727},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.711327314376831},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6915233731269836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5956158638000488},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.5656141638755798},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5490378737449646},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.509823739528656},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48112359642982483},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4777228534221649},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4559427499771118},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4535752534866333},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3709750771522522},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13625583052635193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467147946357727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.711327314376831},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6915233731269836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956158638000488},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.5656141638755798},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5490378737449646},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.509823739528656},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48112359642982483},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4777228534221649},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4559427499771118},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4535752534866333},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3709750771522522},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13625583052635193},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1871840.1871849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871840.1871849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:inria-00555790v1","is_oa":false,"landing_page_url":"https://inria.hal.science/inria-00555790","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc. Workshop on Analytics for Noisy Unstructured Text Data, Oct 2010, Toronto, Canada","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W94225560","https://openalex.org/W146093233","https://openalex.org/W163811496","https://openalex.org/W210770835","https://openalex.org/W562001009","https://openalex.org/W620512191","https://openalex.org/W1508071495","https://openalex.org/W1518579031","https://openalex.org/W1528012351","https://openalex.org/W1572457224","https://openalex.org/W1606054028","https://openalex.org/W1967350923","https://openalex.org/W1985952313","https://openalex.org/W1989302571","https://openalex.org/W2002754742","https://openalex.org/W2017244362","https://openalex.org/W2034537249","https://openalex.org/W2092269560","https://openalex.org/W2109933326","https://openalex.org/W2134659216","https://openalex.org/W2136743866","https://openalex.org/W2141099517","https://openalex.org/W2143345705","https://openalex.org/W2144663841","https://openalex.org/W2146954739","https://openalex.org/W2147880316","https://openalex.org/W2148986421","https://openalex.org/W2164579587","https://openalex.org/W2165771931","https://openalex.org/W2168119002","https://openalex.org/W2597684388","https://openalex.org/W2608050011","https://openalex.org/W2757918699","https://openalex.org/W2998287152","https://openalex.org/W3137298232","https://openalex.org/W4300844795","https://openalex.org/W4301034902","https://openalex.org/W6630461766","https://openalex.org/W6673536509","https://openalex.org/W6681449212"],"related_works":["https://openalex.org/W4250494529","https://openalex.org/W1964783010","https://openalex.org/W2399696375","https://openalex.org/W4284703357","https://openalex.org/W45206245","https://openalex.org/W2211396092","https://openalex.org/W2078793151","https://openalex.org/W2061834489","https://openalex.org/W2751906762","https://openalex.org/W3088215229"],"abstract_inverted_index":{"High-level":[0],"spoken":[1,84,116,146],"document":[2,117,147],"analysis":[3,148],"is":[4,28,34],"required":[5],"in":[6,65,122,156],"many":[7],"applications":[8],"seeking":[9],"access":[10],"to":[11,51,108,167,179,202,237],"the":[12,52,133,193,205,213,220,223,238],"semantic":[13,189],"content":[14],"of":[15,54,59,83,135,164,195,207,222],"audio":[16],"data,":[17],"such":[18,70,149],"as":[19,71,150],"information":[20],"retrieval,":[21],"machine":[22,169],"translation":[23],"or":[24],"automatic":[25,42,110,245],"summarization.":[26],"It":[27],"nevertheless":[29],"a":[30,106,124,168],"difficult":[31],"task":[32],"that":[33,63,86,129,141],"generally":[35],"based":[36,172,191],"on":[37,139,173,192,212],"transcripts":[38,49,112],"provided":[39,242],"by":[40,91,243],"an":[41,244],"speech":[43,111,246],"recognition":[44,61,200,247],"system.":[45,248],"Unlike":[46],"standard":[47,180],"texts,":[48],"belong":[50],"category":[53],"highly":[55],"noisy":[56],"data":[57],"because":[58],"word":[60],"errors":[62],"affect,":[64],"particular,":[66],"very":[67],"significant":[68],"words":[69,140],"named":[72,151,198,208,232],"entities":[73],"(e.g.":[74],"person's":[75],"names,":[76],"locations,":[77],"organizations).":[78],"Transcripts":[79],"also":[80],"contain":[81],"specificities":[82],"language":[85,93],"make":[87],"ineffective":[88],"their":[89],"processing":[90,94],"natural":[92],"tools":[95],"designed":[96],"for":[97,113,144,228],"texts.":[98],"To":[99],"overcome":[100],"these":[101],"issues,":[102],"this":[103],"paper":[104],"proposes":[105],"method":[107,120,171],"reshape":[109],"robust":[114,197],"high-level":[115,145],"analysis.":[118],"The":[119,153],"consists":[121,155],"conceiving":[123],"new":[125,188],"word-level":[126,225],"confidence":[127,226,240],"measure":[128,227,241],"may":[130],"efficiently":[131],"ensure":[132],"reliability":[134,206],"transcribed":[136],"words,":[137],"focusing":[138],"are":[142],"relevant":[143],"entities.":[152,209],"approach":[154],"combining":[157],"different":[158],"features":[159,181,190],"collected":[160],"from":[161],"various":[162],"sources":[163],"knowledge":[165],"thanks":[166],"learning":[170],"conditional":[174],"random":[175],"fields.":[176],"In":[177],"addition":[178],"(morphosyntactic,":[182],"linguistic":[183],"and":[184,231],"phonetic),":[185],"we":[186],"introduce":[187],"decisions":[194],"three":[196],"entity":[199,233],"systems":[201],"better":[203],"estimate":[204],"Experiments,":[210],"conducted":[211],"French":[214],"broadcast":[215],"news":[216],"corpus":[217],"ESTER,":[218],"demonstrate":[219],"added-value":[221],"proposed":[224],"error":[229],"detection":[230],"recognition,":[234],"with":[235],"respect":[236],"basic":[239]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}