{"id":"https://openalex.org/W18656911","doi":"https://doi.org/10.21437/interspeech.2007-404","title":"Text island spotting in large speech databases","display_name":"Text island spotting in large speech databases","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W18656911","doi":"https://doi.org/10.21437/interspeech.2007-404","mag":"18656911"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-404","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01318080","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113675850","display_name":"Benjamin Lecouteux","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"B. Lecouteux","raw_affiliation_strings":["GETALP - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (GETALP-LIG - 110 av. de la Chimie - Domaine Universitaire - BP 53 - 38041 Grenoble - cedex 9 - France)","LIG - Laboratoire d'Informatique de Grenoble (UMR 5217 - Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d\u2019H\u00e8res \r\nAdresse postale : CS 40700 - 38058 Grenoble cedex 9 - France \r\nT\u00e9l. : 04 57 42 14 00 - France)","UGA [2016-2019] - Universit\u00e9 Grenoble Alpes [2016-2019] (38058 Grenoble cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GETALP - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (GETALP-LIG - 110 av. de la Chimie - Domaine Universitaire - BP 53 - 38041 Grenoble - cedex 9 - France)","institution_ids":["https://openalex.org/I4210104430"]},{"raw_affiliation_string":"LIG - Laboratoire d'Informatique de Grenoble (UMR 5217 - Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d\u2019H\u00e8res \r\nAdresse postale : CS 40700 - 38058 Grenoble cedex 9 - France \r\nT\u00e9l. : 04 57 42 14 00 - France)","institution_ids":["https://openalex.org/I4210104430"]},{"raw_affiliation_string":"UGA [2016-2019] - Universit\u00e9 Grenoble Alpes [2016-2019] (38058 Grenoble cedex - France)","institution_ids":["https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050508708","display_name":"Georges Linar\u00e8s","orcid":"https://orcid.org/0000-0001-8049-9056"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Georges Linar\u00e8s","raw_affiliation_strings":["LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087808388","display_name":"Fr\u00e9d\u00e9ric Beaugendre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9ric Beaugendre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053069752","display_name":"Pascal Noc\u00e9ra","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pascal Nocera","raw_affiliation_strings":["LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)","institution_ids":["https://openalex.org/I4210119991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4451,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.5419285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1318","last_page":"1321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/spotting","display_name":"Spotting","score":0.9292079210281372},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8254111409187317},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7235393524169922},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.6597772836685181},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5823497772216797},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5622588992118835},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5592359900474548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.543947696685791},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4870932102203369},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4473933279514313},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3348190188407898},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32110005617141724},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07964131236076355}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9292079210281372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8254111409187317},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7235393524169922},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.6597772836685181},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5823497772216797},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5622588992118835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5592359900474548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.543947696685791},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4870932102203369},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4473933279514313},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3348190188407898},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32110005617141724},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07964131236076355},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2007-404","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.625.7294","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.625.7294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lia.univ-avignon.fr/fileadmin/documents/Users/Intranet/chercheurs/linares/Publis/Benj_INTER07.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01318080v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01318080","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":"INTERSPEECH, Aug 2007, Anvers, Belgium","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-02088836v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02088836","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":"Interspeech","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01318080v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01318080","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":"INTERSPEECH, Aug 2007, Anvers, Belgium","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W142887051","https://openalex.org/W160722039","https://openalex.org/W1975113979","https://openalex.org/W1988596541","https://openalex.org/W2097470427","https://openalex.org/W2120358855","https://openalex.org/W2142228786","https://openalex.org/W2143577772","https://openalex.org/W2157598242","https://openalex.org/W4300622938"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"This":[0,51],"paper":[1],"addresses":[2],"the":[3,30,57,71,100,106,110,114,120],"problem":[4],"of":[5,32,68,88,94],"using":[6],"journalist":[7],"prompts":[8],"or":[9],"closed":[10,127],"captions":[11],"to":[12,48,78],"build":[13],"corpora":[14],"for":[15],"training":[16],"speech":[17,125],"recognition":[18],"systems.":[19],"Generally,":[20],"these":[21],"text":[22,102],"documents":[23],"are":[24],"imperfect":[25],"tran-scripts":[26],"which":[27],"suffer":[28],"from":[29,70],"lack":[31],"timestamps.":[33],"We":[34],"propose":[35],"a":[36,39,44,64,92],"method":[37,52],"combining":[38],"driven":[40,112],"decoding":[41,111],"algorithm":[42],"and":[43,62],"fast-match":[45],"process":[46],"allowing":[47],"spot":[49],"text-segments.":[50],"is":[53],"evaluated":[54],"both":[55],"on":[56,63,98],"French":[58],"ESTER":[59],"([4])":[60],"corpus":[61,129],"large":[65],"database":[66],"composed":[67],"records":[69],"Radio":[72],"Television":[73],"Belge":[74],"Francophone":[75],"(RTBF)":[76],"associated":[77],"real":[79,101],"prompts.":[80],"Results":[81],"show":[82],"very":[83],"good":[84],"performance":[85],"in":[86],"terms":[87],"spotting;":[89],"we":[90],"observed":[91],"F-measure":[93],"about":[95],"98":[96],"%":[97],"spotting":[99],"island":[103,117],"provided":[104],"by":[105,113],"RTBF":[107],"corpus.":[108],"Moreover,":[109],"im-perfect":[115],"transcript":[116],"outperforms":[118],"significantly":[119],"baseline":[121],"system.":[122],"Index":[123],"Terms:":[124],"recognition,":[126],"captioning,":[128],"building":[130]},"counts_by_year":[{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
