{"id":"https://openalex.org/W10968626","doi":"https://doi.org/10.21437/eurospeech.2003-396","title":"Speech starter: noise-robust endpoint detection by using filled pauses","display_name":"Speech starter: noise-robust endpoint detection by using filled pauses","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W10968626","doi":"https://doi.org/10.21437/eurospeech.2003-396","mag":"10968626"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-396","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5024192856","display_name":"Koji Kitayama","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Koji Kitayama","raw_affiliation_strings":[],"affiliations":[]},{"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 of Advanced Industrial Science and Techno"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Techno","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108574981","display_name":"Katunobu Itou","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":false,"raw_author_name":"Katunobu Itou","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Techno"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Techno","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024192856"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8889,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.7220652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1237","last_page":"1240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9965000152587891,"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":0.8219588398933411},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8098568916320801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7309683561325073},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6309265494346619},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6282545924186707},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.45077845454216003},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4496777057647705},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42585307359695435},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3933681845664978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3017290234565735},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12077471613883972}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8219588398933411},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8098568916320801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7309683561325073},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6309265494346619},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6282545924186707},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.45077845454216003},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4496777057647705},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42585307359695435},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3933681845664978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3017290234565735},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12077471613883972},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2003-396","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.1472","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.1472","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/EUROSPEECH2003kitayama.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W10719946","https://openalex.org/W57094479","https://openalex.org/W198720948","https://openalex.org/W1502984613","https://openalex.org/W1521340514","https://openalex.org/W1569306752","https://openalex.org/W1921634150","https://openalex.org/W2032474878","https://openalex.org/W2117321034","https://openalex.org/W2121715942","https://openalex.org/W2130168793","https://openalex.org/W4285719527"],"related_works":["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/W1151175420","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"a":[5,28,31,57,68,71,78,92,108,117,139],"speech":[6,10,19,23,53,110,150],"interface":[7,111],"function,":[8],"called":[9],"starter,":[11],"that":[12,144],"enables":[13,56],"noise-robust":[14],"endpoint":[15,96],"(utterance)":[16],"detection":[17,43,97],"for":[18],"recognition.":[20],"When":[21],"current":[22],"recognizers":[24],"are":[25],"used":[26,76],"in":[27,91,133],"noisy":[29,93,141],"environment,":[30,94],"typical":[32],"recognition":[33,146],"error":[34,147],"is":[35,44,75,98,114],"caused":[36],"by":[37,49,66],"incorrect":[38],"endpoints":[39],"because":[40,116],"their":[41],"automatic":[42],"likely":[45],"to":[46,59,80,120],"be":[47,88],"disturbed":[48],"non-stationary":[50],"noises.":[51],"The":[52],"starter":[54,101,151],"function":[55],"user":[58],"specify":[60],"the":[61,104,127,145],"beginning":[62,128],"of":[63,106,129],"each":[64],"utterance":[65],"uttering":[67],"filler":[69],"with":[70,149,155],"filled":[72,85,122],"pause,":[73],"which":[74],"as":[77],"trigger":[79],"start":[81],"speech-recognition":[82],"processes.":[83],"Since":[84],"pauses":[86,123],"can":[87],"detected":[89],"robustly":[90],"practical":[95],"achieved.":[99],"Speech":[100],"also":[102],"offers":[103],"advantage":[105],"providing":[107],"hands-free":[109],"and":[112],"it":[113],"user-friendly":[115],"speaker":[118],"tends":[119],"utter":[121],"(e.g.,":[124],"\u201cer...\u201d)":[125],"at":[126],"utterances":[130],"when":[131],"hesitating":[132],"human-human":[134],"communication.":[135],"Experimental":[136],"results":[137],"from":[138],"10-dB-SNR":[140],"environment":[142],"show":[143],"rate":[148],"was":[152],"lower":[153],"than":[154],"conventional":[156],"endpoint-detection":[157],"methods.":[158],"1.":[159]},"counts_by_year":[{"year":2019,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}