{"id":"https://openalex.org/W2170227627","doi":"https://doi.org/10.1109/icassp.2009.4960581","title":"The use of acoustically detected filled and silent pauses in spontaneous speech recognition","display_name":"The use of acoustically detected filled and silent pauses in spontaneous speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2170227627","doi":"https://doi.org/10.1109/icassp.2009.4960581","mag":"2170227627"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5006504365","display_name":"Jun Ogata","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jun Ogata","raw_affiliation_strings":["National Institute for Advanced Industrial Science and Technology, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute for Advanced Industrial Science and Technology, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute for Advanced Industrial Science and Technology, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute for Advanced Industrial Science and Technology, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108574981","display_name":"Katunobu Itou","orcid":null},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katunobu Itou","raw_affiliation_strings":["Hosei University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Hosei University, Tokyo, Japan","institution_ids":["https://openalex.org/I204291657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006504365"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":1.3549,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85975521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"31","issue":null,"first_page":"4305","last_page":"4308"},"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9983999729156494,"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/speech-recognition","display_name":"Speech recognition","score":0.78968346118927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.754116415977478},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.742398738861084},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.515356719493866},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4850863516330719},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4331704080104828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32683098316192627},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06528225541114807}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.78968346118927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754116415977478},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.742398738861084},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.515356719493866},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4850863516330719},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4331704080104828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32683098316192627},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06528225541114807},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.7045","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.7045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://staff.aist.go.jp/m.goto/PAPER/ICASSP2009ogata.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W197872364","https://openalex.org/W198720948","https://openalex.org/W272928725","https://openalex.org/W1507423501","https://openalex.org/W1979065632","https://openalex.org/W2091098478","https://openalex.org/W2124246394","https://openalex.org/W2133054063","https://openalex.org/W2204988020","https://openalex.org/W2405110524","https://openalex.org/W4250059583","https://openalex.org/W6608075110","https://openalex.org/W6688046271","https://openalex.org/W6713305007"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"In":[0,28],"recognizing":[1],"spontaneous":[2,95],"speech,":[3],"the":[4,37,79,83,87,93,98,101],"performance":[5,38],"of":[6,39,89,100],"typical":[7,72],"speech":[8,41,73,96],"recognizers":[9],"tends":[10],"to":[11],"be":[12],"degraded":[13],"by":[14,43,62],"filled":[15,48],"and":[16,45,52,76],"silent":[17,53],"pauses,":[18],"which":[19],"are":[20],"hesitation":[21],"phenomena":[22],"frequently":[23],"occurred":[24],"in":[25,68],"such":[26],"speech.":[27],"this":[29],"paper,":[30],"we":[31],"present":[32],"a":[33,40,64,71],"method":[34,57,103],"for":[35],"improving":[36],"recognizer":[42],"detecting":[44],"handling":[46],"both":[47],"pauses":[49,61],"(lengthened":[50],"vowels)":[51],"(unfilled)":[54],"pauses.":[55],"Our":[56],"automatically":[58],"detects":[59],"these":[60],"using":[63,92],"bottom-up":[65],"acoustical":[66],"analysis":[67],"parallel":[69],"with":[70],"decoding":[74,84],"process,":[75],"then":[77],"incorporates":[78],"detected":[80],"results":[81,88],"into":[82],"process.":[85],"From":[86],"experiments":[90],"conducted":[91],"CIAIR":[94],"corpus,":[97],"effectiveness":[99],"proposed":[102],"was":[104],"confirmed.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
