{"id":"https://openalex.org/W4388623407","doi":"https://doi.org/10.1109/ro-man57019.2023.10309547","title":"A Semi-Real-Time Method for Social Robots to Detect and Locate Overlapping Speech Events","display_name":"A Semi-Real-Time Method for Social Robots to Detect and Locate Overlapping Speech Events","publication_year":2023,"publication_date":"2023-08-28","ids":{"openalex":"https://openalex.org/W4388623407","doi":"https://doi.org/10.1109/ro-man57019.2023.10309547"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man57019.2023.10309547","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ro-man57019.2023.10309547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.vu.nl/en/publications/7b854b47-32f9-4399-a3f7-8b011f4538a5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100387803","display_name":"Yue Li","orcid":"https://orcid.org/0000-0002-5624-7235"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Yue Li","raw_affiliation_strings":["Vrije Universiteit Amsterdam,Faculty of Science, Computer Science,Amsterdam,The Netherlands,1081 HV"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam,Faculty of Science, Computer Science,Amsterdam,The Netherlands,1081 HV","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071518251","display_name":"Koen V. Hindriks","orcid":"https://orcid.org/0000-0002-5707-5236"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Koen Hindriks","raw_affiliation_strings":["Vrije Universiteit Amsterdam,Faculty of Science, Computer Science,Amsterdam,The Netherlands,1081 HV"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam,Faculty of Science, Computer Science,Amsterdam,The Netherlands,1081 HV","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063456893","display_name":"Florian Kunneman","orcid":"https://orcid.org/0000-0002-1932-3200"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Florian Kunneman","raw_affiliation_strings":["Vrije Universiteit Amsterdam,Faculty of Science, Computer Science,Amsterdam,The Netherlands,1081 HV"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam,Faculty of Science, Computer Science,Amsterdam,The Netherlands,1081 HV","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100387803"],"corresponding_institution_ids":["https://openalex.org/I865915315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15837048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2086","last_page":"2093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8314151167869568},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6314888596534729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6295738220214844},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5328861474990845},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.51556396484375},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4924095869064331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4440154433250427},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39182400703430176},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3350543975830078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8314151167869568},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6314888596534729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6295738220214844},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5328861474990845},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.51556396484375},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4924095869064331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4440154433250427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39182400703430176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3350543975830078},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ro-man57019.2023.10309547","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ro-man57019.2023.10309547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/7b854b47-32f9-4399-a3f7-8b011f4538a5","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/7b854b47-32f9-4399-a3f7-8b011f4538a5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, Y, Hindriks, K & Kunneman, F 2023, A Semi-Real-Time Method for Social Robots to Detect and Locate Overlapping Speech Events. in 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) : [Proceedings]. IEEE International Workshop on Robot and Human Communication, RO-MAN, IEEE Computer Society, pp. 2086-2093, 32nd IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2023, Busan, Korea, Republic of, 28/08/23. https://doi.org/10.1109/RO-MAN57019.2023.10309547","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research.vu.nl:openaire/7b854b47-32f9-4399-a3f7-8b011f4538a5","is_oa":true,"landing_page_url":"https://research.vu.nl/files/356264872/A_Semi-Real-Time_Method_for_Social_Robots_to_Detect_and_Locate_Overlapping_Speech_Events.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, Y, Hindriks, K & Kunneman, F 2023, A Semi-Real-Time Method for Social Robots to Detect and Locate Overlapping Speech Events. in 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) : [Proceedings]. IEEE International Workshop on Robot and Human Communication, RO-MAN, IEEE Computer Society, pp. 2086-2093, 32nd IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2023, Busan, Korea, Republic of, 28/08/23. https://doi.org/10.1109/RO-MAN57019.2023.10309547","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research.vu.nl:publications/7b854b47-32f9-4399-a3f7-8b011f4538a5","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/7b854b47-32f9-4399-a3f7-8b011f4538a5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, Y, Hindriks, K & Kunneman, F 2023, A Semi-Real-Time Method for Social Robots to Detect and Locate Overlapping Speech Events. in 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) : [Proceedings]. IEEE International Workshop on Robot and Human Communication, RO-MAN, IEEE Computer Society, pp. 2086-2093, 32nd IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2023, Busan, Korea, Republic of, 28/08/23. https://doi.org/10.1109/RO-MAN57019.2023.10309547","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/7b854b47-32f9-4399-a3f7-8b011f4538a5","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/7b854b47-32f9-4399-a3f7-8b011f4538a5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, Y, Hindriks, K & Kunneman, F 2023, A Semi-Real-Time Method for Social Robots to Detect and Locate Overlapping Speech Events. in 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) : [Proceedings]. IEEE International Workshop on Robot and Human Communication, RO-MAN, IEEE Computer Society, pp. 2086-2093, 32nd IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2023, Busan, Korea, Republic of, 28/08/23. https://doi.org/10.1109/RO-MAN57019.2023.10309547","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2047527596","https://openalex.org/W2100818340","https://openalex.org/W2101856597","https://openalex.org/W2104484061","https://openalex.org/W2104866265","https://openalex.org/W2114863372","https://openalex.org/W2168483376","https://openalex.org/W2400339399","https://openalex.org/W2592008997","https://openalex.org/W2742299865","https://openalex.org/W2772736377","https://openalex.org/W2794289187","https://openalex.org/W2810934215","https://openalex.org/W2963840672","https://openalex.org/W3016037102","https://openalex.org/W3105684258","https://openalex.org/W3113688134","https://openalex.org/W3176830388","https://openalex.org/W3191009323","https://openalex.org/W3198730349","https://openalex.org/W3205596865","https://openalex.org/W4233329660","https://openalex.org/W4285150836","https://openalex.org/W4287120192","https://openalex.org/W6696085341","https://openalex.org/W6761012586","https://openalex.org/W6796679619"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W4239306820","https://openalex.org/W2947043951","https://openalex.org/W4312417841","https://openalex.org/W2062195135"],"abstract_inverted_index":{"It":[0],"is":[1,64,154],"useful":[2],"for":[3,68,87,172],"a":[4,23,46,51,69],"social":[5],"robot":[6],"to":[7,37,50],"detect":[8],"and":[9,28,83,97,120,136,153],"locate":[10],"users":[11],"based":[12],"on":[13,41,45,77,112],"their":[14,61,137],"speech.":[15,30],"Notable":[16],"challenges":[17],"hampering":[18],"the":[19,78,94,104,130,158,166,174,177],"effective":[20],"localization":[21],"of":[22,118,126,132,176],"speaker":[24],"are":[25],"background":[26],"noise":[27],"overlapping":[29,121],"Convolutional":[31],"Neural":[32],"Networks":[33],"(CNNs)":[34],"have":[35],"shown":[36],"yield":[38],"good":[39],"performance":[40],"locating":[42,150],"single":[43],"speakers":[44,90,152],"curated":[47],"dataset,":[48],"but":[49],"lesser":[52],"extent":[53],"in":[54,72,93,124,149,165],"scenarios":[55],"with":[56,116],"two":[57,151],"speakers.":[58],"In":[59],"addition,":[60],"computational":[62,99],"cost":[63],"still":[65],"too":[66],"high":[67],"timely":[70],"reaction":[71],"real-world":[73],"settings.":[74],"We":[75,108],"build":[76],"current":[79],"state-of-the-art":[80],"CNN":[81],"approach,":[82],"propose":[84],"several":[85],"improvements":[86],"distinguishing":[88],"multiple":[89],"by":[91,101],"time-alignment":[92],"input":[95,105,167],"representation":[96,168],"reducing":[98],"costs":[100],"considerably":[102,155],"shortening":[103],"audio":[106],"blocks.":[107],"evaluate":[109],"this":[110],"approach":[111,145],"an":[113],"existing":[114],"dataset":[115],"blocks":[117],"noisy":[119],"speech":[122,134],"recorded":[123],"rooms":[125],"different":[127],"sizes,":[128],"predicting":[129,173],"number":[131],"active":[133],"events":[135],"azimuth":[138],"locations.":[139],"The":[140,162],"results":[141],"show":[142],"that":[143],"our":[144],"outperforms":[146],"other":[147],"approaches":[148],"faster":[156],"than":[157],"best-performing":[159],"alternative":[160],"approach.":[161],"time-domain":[163],"information":[164],"was":[169],"found":[170],"essential":[171],"location":[175],"signal":[178],"source.":[179]},"counts_by_year":[],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}