{"id":"https://openalex.org/W2598963337","doi":"https://doi.org/10.1109/kst.2017.7886109","title":"Reducing waiting time in automatic captioned relay service using short pause in voice activity detection","display_name":"Reducing waiting time in automatic captioned relay service using short pause in voice activity detection","publication_year":2017,"publication_date":"2017-02-01","ids":{"openalex":"https://openalex.org/W2598963337","doi":"https://doi.org/10.1109/kst.2017.7886109","mag":"2598963337"},"language":"en","primary_location":{"id":"doi:10.1109/kst.2017.7886109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst.2017.7886109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 9th International Conference on Knowledge and Smart Technology (KST)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5061912115","display_name":"Kiettiphong Manovisut","orcid":null},"institutions":[{"id":"https://openalex.org/I108108428","display_name":"Thammasat University","ror":"https://ror.org/002yp7f20","country_code":"TH","type":"education","lineage":["https://openalex.org/I108108428"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Kiettiphong Manovisut","raw_affiliation_strings":["Department of Computer Science, Thammasat University, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Thammasat University, Thailand","institution_ids":["https://openalex.org/I108108428"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035810881","display_name":"Nattanun Thatphithakkul","orcid":"https://orcid.org/0000-0001-8240-2772"},"institutions":[{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Nattanun Thatphithakkul","raw_affiliation_strings":["National Electronics and Computer Technology Center, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Electronics and Computer Technology Center, Thailand","institution_ids":["https://openalex.org/I14316845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013324722","display_name":"Pokpong Songmuang","orcid":"https://orcid.org/0000-0002-4831-686X"},"institutions":[{"id":"https://openalex.org/I108108428","display_name":"Thammasat University","ror":"https://ror.org/002yp7f20","country_code":"TH","type":"education","lineage":["https://openalex.org/I108108428"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Pokpong Songmuang","raw_affiliation_strings":["Department of Computer Science, Thammasat University, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Thammasat University, Thailand","institution_ids":["https://openalex.org/I108108428"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"216","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9929999709129333,"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/relay","display_name":"Relay","score":0.836524486541748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7887511849403381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7274340391159058},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6313721537590027},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.5711873769760132},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.37644290924072266},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3433193862438202},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3278431296348572}],"concepts":[{"id":"https://openalex.org/C2778156585","wikidata":"https://www.wikidata.org/wiki/Q174053","display_name":"Relay","level":3,"score":0.836524486541748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887511849403381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7274340391159058},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6313721537590027},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.5711873769760132},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.37644290924072266},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3433193862438202},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3278431296348572},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/kst.2017.7886109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst.2017.7886109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 9th International Conference on Knowledge and Smart Technology (KST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326788","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1994480841","https://openalex.org/W1999454387","https://openalex.org/W2048497537","https://openalex.org/W2109788549","https://openalex.org/W2120979206","https://openalex.org/W2156866340","https://openalex.org/W2164579587","https://openalex.org/W2294012495","https://openalex.org/W2402212287","https://openalex.org/W6648819691","https://openalex.org/W6676413359","https://openalex.org/W6713247406"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2081671587","https://openalex.org/W1151175420","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"The":[0,82],"Automatic":[1,23],"Captioned":[2],"Relay":[3],"Service":[4],"is":[5],"crucial":[6],"for":[7,56],"hearing":[8],"disabilities":[9],"or":[10],"hard-of-hearing":[11],"to":[12,27,30],"communicate":[13],"with":[14,103],"others":[15],"in":[16],"real":[17],"life.":[18],"This":[19,73],"service":[20,44],"uses":[21],"an":[22],"Speech":[24],"Recognition":[25],"(ASR)":[26],"transcribe":[28],"speech":[29,40],"a":[31,54,58,64],"caption.":[32],"If":[33],"can":[34],"reduce":[35],"waiting":[36,76,93],"time":[37,77,94],"from":[38],"non-streaming":[39],"recognition,":[41],"the":[42,79,87,97],"relay":[43],"will":[45],"support":[46],"more":[47],"users.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"proposed":[53],"method":[55,74,89],"improving":[57],"voice":[59],"activity":[60],"detection":[61],"(VAD)":[62],"using":[63],"short":[65],"pause":[66],"as":[67],"endpoint":[68],"based":[69],"on":[70],"dual-threshold":[71],"method.":[72],"reduces":[75,90],"of":[78,92,99],"captions":[80,100],"results.":[81],"experimental":[83],"results":[84],"show":[85],"that":[86],"propose":[88],"19.10%":[91],"without":[95],"losing":[96],"accuracy":[98],"when":[101],"compare":[102],"traditional":[104],"VAD.":[105]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
