{"id":"https://openalex.org/W3007163346","doi":"https://doi.org/10.1109/asru46091.2019.9003816","title":"Improving Speech-Based End-of-Turn Detection Via Cross-Modal Representation Learning with Punctuated Text Data","display_name":"Improving Speech-Based End-of-Turn Detection Via Cross-Modal Representation Learning with Punctuated Text Data","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007163346","doi":"https://doi.org/10.1109/asru46091.2019.9003816","mag":"3007163346"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003816","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027118468","display_name":"Mana Ihori","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mana Ihori","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009756622","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0001-7442-4912"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061074419","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0002-3971-0654"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101707624","display_name":"Ryo Ishii","orcid":"https://orcid.org/0009-0001-3849-1656"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Ishii","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109336432","display_name":"Takanobu Oba","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanobu Oba","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004045909","display_name":"Ryuichiro Higashinaka","orcid":"https://orcid.org/0000-0002-6994-3977"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuichiro Higashinaka","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1062","last_page":"1069"},"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8137339949607849},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5774841904640198},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5400887131690979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4903841018676758},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4841171205043793},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.46879586577415466},{"id":"https://openalex.org/keywords/data-driven","display_name":"Data-driven","score":0.4273003339767456},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4181334376335144},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4172631502151489}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137339949607849},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5774841904640198},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5400887131690979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4903841018676758},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4841171205043793},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.46879586577415466},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.4273003339767456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4181334376335144},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4172631502151489},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003816","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W1502481855","https://openalex.org/W1504308419","https://openalex.org/W1533504578","https://openalex.org/W1566669007","https://openalex.org/W1932883564","https://openalex.org/W1999454387","https://openalex.org/W2008741806","https://openalex.org/W2087762538","https://openalex.org/W2117278770","https://openalex.org/W2153190547","https://openalex.org/W2161274063","https://openalex.org/W2169187092","https://openalex.org/W2250978584","https://openalex.org/W2398104528","https://openalex.org/W2403332862","https://openalex.org/W2426479676","https://openalex.org/W2513522215","https://openalex.org/W2575282817","https://openalex.org/W2747888173","https://openalex.org/W2748406667","https://openalex.org/W2786387151","https://openalex.org/W2883586237","https://openalex.org/W2886198413","https://openalex.org/W2888525722","https://openalex.org/W2889213362","https://openalex.org/W2889231094","https://openalex.org/W2891328459","https://openalex.org/W2894786240","https://openalex.org/W2902448405","https://openalex.org/W2912937645","https://openalex.org/W2913518575","https://openalex.org/W2938722449","https://openalex.org/W2938728617","https://openalex.org/W2938947737","https://openalex.org/W2950749035","https://openalex.org/W2962699523","https://openalex.org/W2962989741","https://openalex.org/W2963425185","https://openalex.org/W2963571336","https://openalex.org/W2963739817","https://openalex.org/W6601563604","https://openalex.org/W6629991819","https://openalex.org/W6632002277","https://openalex.org/W6677328538","https://openalex.org/W6690924129","https://openalex.org/W6712411474","https://openalex.org/W6713650804","https://openalex.org/W6731992975","https://openalex.org/W6753186555","https://openalex.org/W6756642458","https://openalex.org/W6761607354"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2351687372","https://openalex.org/W2314871050","https://openalex.org/W1998701884"],"abstract_inverted_index":{"This":[0,150],"paper":[1],"presents":[2],"a":[3,34,87,128,132],"novel":[4],"training":[5],"method":[6,121],"for":[7,11,111],"speech-based":[8,29,49,115,155,180],"end-of-turn":[9,30,50,64,79,116,156,181],"detection":[10,31,51,80,157,182],"which":[12],"not":[13,41],"only":[14,56],"manually":[15,62],"annotated":[16,63,71],"speech":[17,43,57,72,91,129,138],"data":[18,24,58,73,98,109,163,198],"sets":[19,25,59,74,110,164],"but":[20],"also":[21],"punctuated":[22,107,161,196],"text":[23,108,133,140,162,197],"are":[26,75],"utilized.":[27],"The":[28],"estimates":[32],"whether":[33],"target":[35],"speaker's":[36],"utterance":[37],"is":[38,104],"ended":[39],"or":[40],"using":[42,55,184],"information.":[44],"In":[45,93,171],"previous":[46],"studies,":[47],"the":[48,68,78,97,119,142,160,193],"models":[52,81,158,183],"were":[53,82],"trained":[54],"that":[60,135,179],"contained":[61],"labels.":[65],"However,":[66],"since":[67],"amounts":[69],"of":[70,90,195],"often":[76],"limited,":[77],"unable":[83],"to":[84,95,105,126,153],"correctly":[85],"handle":[86],"wide":[88],"variety":[89],"patterns.":[92],"order":[94],"mitigate":[96],"scarcity":[99],"problem,":[100],"our":[101],"key":[102],"idea":[103],"leverage":[106],"building":[112],"more":[113],"effective":[114],"detection.":[117,170],"Therefore,":[118],"proposed":[120],"introduces":[122],"cross-modal":[123],"representation":[124],"learning":[125],"construct":[127],"encoder":[130,134],"and":[131,139],"can":[136,189],"map":[137],"with":[141],"same":[143],"lexical":[144],"information":[145],"into":[146],"similar":[147],"vector":[148],"representations.":[149],"enables":[151],"us":[152],"train":[154],"from":[159],"by":[165],"tackling":[166],"text-based":[167],"sentence":[168],"boundary":[169],"experiments":[172],"on":[173],"contact":[174],"center":[175],"calls,":[176],"we":[177],"show":[178],"hierarchical":[185],"recurrent":[186],"neural":[187],"networks":[188],"be":[190],"improved":[191],"through":[192],"use":[194],"sets.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}