{"id":"https://openalex.org/W2100919116","doi":"https://doi.org/10.1109/icassp.2011.5947688","title":"Online detection of vocal Listener Responses with maximum latency constraints","display_name":"Online detection of vocal Listener Responses with maximum latency constraints","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2100919116","doi":"https://doi.org/10.1109/icassp.2011.5947688","mag":"2100919116"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5090176000","display_name":"Daniel Neiberg","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Daniel Neiberg","raw_affiliation_strings":["Department of Speech, Music and Hearing, Royal Institute of Technology, Sweden","Department of Speech, Music and Hearing, Royal Institute of Technology (KTH), Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Speech, Music and Hearing, Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Department of Speech, Music and Hearing, Royal Institute of Technology (KTH), Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068294985","display_name":"Khiet P. Truong","orcid":"https://orcid.org/0000-0002-7243-0523"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Khiet P. Truong","raw_affiliation_strings":["Human Media Interaction, University of Twente, Netherlands","Human Media Interaction, University of Twente, The Netherlands#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Media Interaction, University of Twente, Netherlands","institution_ids":["https://openalex.org/I94624287"]},{"raw_affiliation_string":"Human Media Interaction, University of Twente, The Netherlands#TAB#","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3965,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94527914,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"37","issue":null,"first_page":"5836","last_page":"5839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7265843749046326},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7072451710700989},{"id":"https://openalex.org/keywords/interactivity","display_name":"Interactivity","score":0.6632899045944214},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6444678902626038},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5845643877983093},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.566034197807312},{"id":"https://openalex.org/keywords/human-voice","display_name":"Human voice","score":0.5154803395271301},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5083088278770447},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44815218448638916},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17001193761825562},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.15373706817626953},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09084123373031616},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06838756799697876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7265843749046326},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7072451710700989},{"id":"https://openalex.org/C144430266","wikidata":"https://www.wikidata.org/wiki/Q839721","display_name":"Interactivity","level":2,"score":0.6632899045944214},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6444678902626038},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5845643877983093},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.566034197807312},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.5154803395271301},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5083088278770447},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44815218448638916},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17001193761825562},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.15373706817626953},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09084123373031616},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06838756799697876},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2011.5947688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/dadd51c2-04e3-461a-b7a2-8116fc34df91","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/dadd51c2-04e3-461a-b7a2-8116fc34df91","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neiberg, D & Truong, K P 2011, Online Detection Of Vocal Listener Responses With Maximum Latency Constraints. in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). IEEE, USA, pp. 5836-5839, IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2011, Prague, Czech Republic, 22/05/11. https://doi.org/10.1109/ICASSP.2011.5947688","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.416.7945","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.416.7945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.kth.se/prod/publications/files/3517.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.454.974","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.454.974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.eemcs.utwente.nl/20186/02/05947688.pdf","raw_type":"text"},{"id":"pmh:oai:ris.utwente.nl:publications/dadd51c2-04e3-461a-b7a2-8116fc34df91","is_oa":false,"landing_page_url":"http://eprints.eemcs.utwente.nl/secure2/20186/01/0005836.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W963652032","https://openalex.org/W1741471588","https://openalex.org/W2001292406","https://openalex.org/W2060865824","https://openalex.org/W2085662862","https://openalex.org/W2101349847","https://openalex.org/W2102722370","https://openalex.org/W2109730238","https://openalex.org/W2113332622","https://openalex.org/W2118142207","https://openalex.org/W2131694695","https://openalex.org/W2153635508","https://openalex.org/W3120421331","https://openalex.org/W4255293871","https://openalex.org/W6625207919","https://openalex.org/W6675672356","https://openalex.org/W6676501121","https://openalex.org/W6676779654","https://openalex.org/W7073743773"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W2343205865"],"abstract_inverted_index":{"When":[0],"human":[1,46,47],"listeners":[2],"utter":[3],"Listener":[4,88,99],"Responses":[5,100],"(e.g.":[6],"back-channels":[7],"or":[8,20],"acknowledgments)":[9],"such":[10],"as":[11,87],"'yeah'":[12],"and":[13,61,72],"'mmhmm',":[14],"interlocutors":[15],"commonly":[16],"continue":[17],"to":[18,57,96,116],"speak":[19],"resume":[21],"their":[22],"speech":[23,35,40,55,86],"even":[24],"before":[25],"the":[26],"listener":[27],"has":[28],"finished":[29],"his/her":[30],"response.":[31],"This":[32],"type":[33,53],"of":[34,54,105],"interactivity":[36,56],"results":[37],"in":[38,45,68],"frequent":[39],"overlap":[41],"which":[42,65,82],"is":[43,94],"common":[44],"conversation.":[48],"To":[49],"allow":[50],"for":[51],"this":[52],"occur":[58],"between":[59],"humans":[60],"spoken":[62],"dialog":[63],"systems,":[64],"will":[66],"result":[67],"more":[69],"human-like":[70],"continuous":[71],"smoother":[73],"human-machine":[74],"inter":[75],"action,":[76],"we":[77],"propose":[78],"an":[79,120],"on-line":[80],"classifier":[81],"can":[83],"classify":[84],"incoming":[85],"Responses.":[89],"We":[90],"show":[91],"that":[92],"it":[93],"possible":[95],"detect":[97],"vocal":[98],"using":[101,119],"maximum":[102],"latency":[103],"thresholds":[104],"100-500":[106],"ms,":[107],"thereby":[108],"obtaining":[109],"equal":[110],"error":[111],"rates":[112],"ranging":[113],"from":[114],"34%":[115],"28%":[117],"by":[118],"energy":[121],"based":[122],"voice":[123],"activity":[124],"detector.":[125]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}