{"id":"https://openalex.org/W2096848909","doi":"https://doi.org/10.1109/asru.2009.5372928","title":"Local and global models for spontaneous speech segment detection and characterization","display_name":"Local and global models for spontaneous speech segment detection and characterization","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2096848909","doi":"https://doi.org/10.1109/asru.2009.5372928","mag":"2096848909"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5372928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5372928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & 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/A5102920772","display_name":"Richard Dufour","orcid":"https://orcid.org/0000-0003-1203-9108"},"institutions":[{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Richard Dufour","raw_affiliation_strings":["LIUM, University of Le Mans, France","LIUM - University of Le Mans, France"],"affiliations":[{"raw_affiliation_string":"LIUM, University of Le Mans, France","institution_ids":["https://openalex.org/I234216984"]},{"raw_affiliation_string":"LIUM - University of Le Mans, France","institution_ids":["https://openalex.org/I234216984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081852717","display_name":"Yannick Est\u00e8ve","orcid":"https://orcid.org/0000-0002-3656-8883"},"institutions":[{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yannick Esteve","raw_affiliation_strings":["LIUM, University of Le Mans, France","LIUM - University of Le Mans, France"],"affiliations":[{"raw_affiliation_string":"LIUM, University of Le Mans, France","institution_ids":["https://openalex.org/I234216984"]},{"raw_affiliation_string":"LIUM - University of Le Mans, France","institution_ids":["https://openalex.org/I234216984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089825993","display_name":"Paul Del\u00e9glise","orcid":null},"institutions":[{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Paul Deleglise","raw_affiliation_strings":["LIUM, University of Le Mans, France","LIUM - University of Le Mans, France"],"affiliations":[{"raw_affiliation_string":"LIUM, University of Le Mans, France","institution_ids":["https://openalex.org/I234216984"]},{"raw_affiliation_string":"LIUM - University of Le Mans, France","institution_ids":["https://openalex.org/I234216984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110498175","display_name":"Fr\u00e9d\u00e9ric B\u00e9chet","orcid":null},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Frederic Bechet","raw_affiliation_strings":["LIA, University of Avignon, France"],"affiliations":[{"raw_affiliation_string":"LIA, University of Avignon, France","institution_ids":["https://openalex.org/I198415970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102920772"],"corresponding_institution_ids":["https://openalex.org/I234216984"],"apc_list":null,"apc_paid":null,"fwci":4.1926328,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.95885498,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"558","last_page":"561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9988999962806702,"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":0.791292667388916},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7422294616699219},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.549331784248352},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5214056968688965},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5139009952545166},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5086844563484192},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4999122619628906},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46915045380592346},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4611930847167969},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.45507776737213135},{"id":"https://openalex.org/keywords/speech-error","display_name":"Speech error","score":0.4421236515045166},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4189731478691101},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41264989972114563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4111473560333252},{"id":"https://openalex.org/keywords/repetition","display_name":"Repetition (rhetorical device)","score":0.41006723046302795},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.34758901596069336},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20366361737251282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791292667388916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7422294616699219},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.549331784248352},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5214056968688965},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5139009952545166},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5086844563484192},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4999122619628906},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46915045380592346},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4611930847167969},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.45507776737213135},{"id":"https://openalex.org/C541956065","wikidata":"https://www.wikidata.org/wiki/Q2250680","display_name":"Speech error","level":3,"score":0.4421236515045166},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4189731478691101},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41264989972114563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4111473560333252},{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.41006723046302795},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.34758901596069336},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20366361737251282},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5372928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5372928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W116241127","https://openalex.org/W158673570","https://openalex.org/W177378321","https://openalex.org/W1488153692","https://openalex.org/W1530201261","https://openalex.org/W1656790015","https://openalex.org/W2053154970","https://openalex.org/W2053463056","https://openalex.org/W2109681258","https://openalex.org/W2153072998","https://openalex.org/W2340053531","https://openalex.org/W2403685076","https://openalex.org/W4300936199","https://openalex.org/W6604749681","https://openalex.org/W6629294717","https://openalex.org/W6637000746","https://openalex.org/W6703902498"],"related_works":["https://openalex.org/W2355709873","https://openalex.org/W4312668661","https://openalex.org/W2337605147","https://openalex.org/W2184127972","https://openalex.org/W2036933852","https://openalex.org/W2032286903","https://openalex.org/W1587401114","https://openalex.org/W134179020","https://openalex.org/W2026905833","https://openalex.org/W4389400962"],"abstract_inverted_index":{"Processing":[0],"spontaneous":[1,23,53,125,153],"speech":[2,11,24,54,62,126,154],"is":[3],"one":[4],"of":[5,45,80,85,112,140],"the":[6,40,43,92,152],"many":[7,35],"challenges":[8],"that":[9,71,117,137],"automatic":[10],"recognition":[12],"(ASR)":[13],"systems":[14],"have":[15,37],"to":[16,60,69],"deal":[17],"with.":[18],"The":[19],"main":[20],"evidences":[21],"characterizing":[22,122],"are":[25,79,90,99],"disfluencies":[26],"(filled":[27],"pause,":[28],"repetition,":[29],"repair":[30],"and":[31,34,42,96,114,123],"false":[32],"start)":[33],"studies":[36],"focused":[38],"on":[39],"detection":[41],"correction":[44],"these":[46],"disfluencies.":[47],"In":[48],"this":[49],"study":[50],"we":[51,133],"define":[52],"as":[55,102,104],"unprepared":[56,86],"speech,":[57,87],"in":[58,75],"opposition":[59],"prepared":[61],"where":[63],"utterances":[64],"contain":[65],"well-formed":[66],"sentences":[67],"close":[68],"those":[70],"can":[72,118],"be":[73,119],"found":[74],"written":[76],"documents.":[77],"Disfluencies":[78],"course":[81],"very":[82],"good":[83],"indicators":[84],"however":[88],"they":[89],"not":[91],"only":[93],"ones:":[94],"ungrammaticality":[95],"language":[97],"register":[98],"also":[100],"important":[101],"well":[103],"prosodic":[105],"patterns.":[106],"This":[107],"paper":[108],"proposes":[109],"a":[110,135,141,146],"set":[111],"acoustic":[113],"linguistic":[115],"features":[116],"used":[120],"for":[121],"detecting":[124],"segments":[127],"from":[128],"large":[129],"audio":[130],"databases.":[131],"More,":[132],"introduce":[134],"strategy":[136],"takes":[138],"advantage":[139],"global":[142],"classification":[143],"procfalseess":[144],"using":[145],"probabilistic":[147],"model":[148],"which":[149],"significantly":[150],"improves":[151],"detection.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}