{"id":"https://openalex.org/W201747637","doi":"https://doi.org/10.21437/interspeech.2012-83","title":"Learning when to listen: detecting system-addressed speech in human-human-computer dialog","display_name":"Learning when to listen: detecting system-addressed speech in human-human-computer dialog","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W201747637","doi":"https://doi.org/10.21437/interspeech.2012-83","mag":"201747637"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-83","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-83","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Elizabeth Shriberg","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068709817","display_name":"Dilek Hakkani\u2010T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dilek Hakkani-T\u00fcr","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003679010","display_name":"Larry Heck","orcid":"https://orcid.org/0000-0003-3358-6362"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Larry Heck","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":2.6017,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.90434342,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"334","last_page":"337"},"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":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.8336260318756104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7029271125793457},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.6428608894348145},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6324154138565063},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5988275408744812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5622490048408508},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4982917308807373},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45022672414779663},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17824864387512207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8336260318756104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7029271125793457},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.6428608894348145},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6324154138565063},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5988275408744812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5622490048408508},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4982917308807373},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45022672414779663},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17824864387512207},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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":1,"locations":[{"id":"doi:10.21437/interspeech.2012-83","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-83","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W8942335","https://openalex.org/W153034550","https://openalex.org/W601101228","https://openalex.org/W1845380253","https://openalex.org/W2053463056","https://openalex.org/W2097464745","https://openalex.org/W2105359808","https://openalex.org/W2107713197","https://openalex.org/W2115829091","https://openalex.org/W2143402463","https://openalex.org/W2144155486","https://openalex.org/W2153410846","https://openalex.org/W2295504855","https://openalex.org/W2978847058","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1769849273","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W1967477266","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817"],"abstract_inverted_index":{"New":[0],"challenges":[1],"arise":[2],"for":[3,110,147,160],"addressee":[4],"detection":[5],"when":[6],"multiple":[7],"people":[8],"interact":[9],"jointly":[10],"with":[11,54,97,117,152],"a":[12,31,70,78,83,100,140],"spoken":[13],"dialog":[14],"system":[15],"using":[16,38,86],"unconstrained":[17],"natural":[18],"language.":[19],"We":[20],"study":[21],"the":[22],"problem":[23],"of":[24,34],"discriminating":[25],"computer-directed":[26],"from":[27,61,90],"human-directed":[28],"speech":[29,57,116],"in":[30],"new":[32],"corpus":[33],"human-human-computer":[35],"(H-H-C)":[36],"dialog,":[37],"lexical":[39,62,84,106,153],"and":[40],"prosodic":[41,44,66,103],"features.":[42],"The":[43],"features":[45,63,67,75],"use":[46],"no":[47],"word,":[48],"context,":[49],"or":[50],"speaker":[51],"information.":[52],"Results":[53],"19%":[55],"WER":[56],"recognition":[58],"show":[59],"improvements":[60],"(EER=23.1%)":[64],"to":[65,69,92,155],"(EER=12.6%)":[68],"combined":[71],"model":[72,85],"(EER=11.1%).":[73],"Prosodic":[74,120],"also":[76],"provide":[77,144],"35%":[79],"error":[80],"reduction":[81],"over":[82],"true":[87],"words":[88],"(EER":[89],"10.2%":[91],"6.7%).":[93],"Modeling":[94],"energy":[95],"contours":[96],"GMMs":[98],"provides":[99],"particularly":[101],"good":[102],"model.":[104],"While":[105],"models":[107,121,151,154],"perform":[108],"well":[109],"commands,":[111],"they":[112,133],"confuse":[113],"free-form":[114],"system-directed":[115],"human-human":[118],"speech.":[119],"dramatically":[122],"reduce":[123],"these":[124],"confusions,":[125],"implying":[126],"that":[127],"users":[128],"change":[129],"speaking":[130,157],"style":[131,158],"as":[132],"shift":[134],"addressees":[135],"(computer":[136],"versus":[137],"human)":[138],"within":[139],"session.":[141],"Overall":[142],"results":[143],"strong":[145],"support":[146],"combining":[148],"simple":[149],"acoustic-prosodic":[150],"detect":[156],"differences":[159],"this":[161],"task.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}