{"id":"https://openalex.org/W4403919165","doi":"https://doi.org/10.1109/ro-man60168.2024.10731262","title":"A Near-Real-Time Processing Ego Speech Filtering Pipeline Designed for Speech Interruption During Human-Robot Interaction","display_name":"A Near-Real-Time Processing Ego Speech Filtering Pipeline Designed for Speech Interruption During Human-Robot Interaction","publication_year":2024,"publication_date":"2024-08-26","ids":{"openalex":"https://openalex.org/W4403919165","doi":"https://doi.org/10.1109/ro-man60168.2024.10731262"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man60168.2024.10731262","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ro-man60168.2024.10731262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)","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/30b4f47e-4fbd-4c0d-88cf-44d4bf0c01b1","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,Department of Computer Science,Amsterdam,The Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam,Department of Computer Science,Amsterdam,The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063456893","display_name":"Florian Kunneman","orcid":"https://orcid.org/0000-0002-1932-3200"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Florian A. Kunneman","raw_affiliation_strings":["Utrecht University,Department of Languages, Literature and Communication,Utrecht,The Netherlands"],"affiliations":[{"raw_affiliation_string":"Utrecht University,Department of Languages, Literature and Communication,Utrecht,The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","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 V. Hindriks","raw_affiliation_strings":["Vrije Universiteit Amsterdam,Department of Computer Science,Amsterdam,The Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam,Department of Computer Science,Amsterdam,The Netherlands","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":0.22842939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1370","last_page":"1377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9711999893188477,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9711999893188477,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9642000198364258,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9573000073432922,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/pipeline","display_name":"Pipeline (software)","score":0.7352731227874756},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7163841128349304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.628417432308197},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5905813574790955},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5389910340309143},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5362450480461121},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5266653895378113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35360628366470337}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7352731227874756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163841128349304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.628417432308197},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5905813574790955},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5389910340309143},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5362450480461121},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5266653895378113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35360628366470337},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ro-man60168.2024.10731262","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ro-man60168.2024.10731262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/30b4f47e-4fbd-4c0d-88cf-44d4bf0c01b1","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/30b4f47e-4fbd-4c0d-88cf-44d4bf0c01b1","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, Kunneman, F A & Hindriks, K V 2024, A Near-Real-Time Processing Ego Speech Filtering Pipeline Designed for Speech Interruption During Human-Robot Interaction. in 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN) : [Proceedings]. IEEE International Workshop on Robot and Human Communication (RO-MAN), IEEE Computer Society, pp. 1370-1377, 33rd IEEE International Conference on Robot and Human Interactive Communication, ROMAN 2024, Pasadena, United States, 26/08/24. https://doi.org/10.1109/RO-MAN60168.2024.10731262","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research.vu.nl:openaire/30b4f47e-4fbd-4c0d-88cf-44d4bf0c01b1","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/30b4f47e-4fbd-4c0d-88cf-44d4bf0c01b1","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, Kunneman, F A & Hindriks, K V 2024, A Near-Real-Time Processing Ego Speech Filtering Pipeline Designed for Speech Interruption During Human-Robot Interaction. in 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN) : [Proceedings]. IEEE International Workshop on Robot and Human Communication (RO-MAN), IEEE Computer Society, pp. 1370-1377, 33rd IEEE International Conference on Robot and Human Interactive Communication, ROMAN 2024, Pasadena, United States, 26/08/24. https://doi.org/10.1109/RO-MAN60168.2024.10731262","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/30b4f47e-4fbd-4c0d-88cf-44d4bf0c01b1","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/30b4f47e-4fbd-4c0d-88cf-44d4bf0c01b1","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, Kunneman, F A & Hindriks, K V 2024, A Near-Real-Time Processing Ego Speech Filtering Pipeline Designed for Speech Interruption During Human-Robot Interaction. in 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN) : [Proceedings]. IEEE International Workshop on Robot and Human Communication (RO-MAN), IEEE Computer Society, pp. 1370-1377, 33rd IEEE International Conference on Robot and Human Interactive Communication, ROMAN 2024, Pasadena, United States, 26/08/24. https://doi.org/10.1109/RO-MAN60168.2024.10731262","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W317957491","https://openalex.org/W1141027450","https://openalex.org/W1494198834","https://openalex.org/W1502692652","https://openalex.org/W1967614663","https://openalex.org/W2098463040","https://openalex.org/W2221409856","https://openalex.org/W2333796428","https://openalex.org/W2460742184","https://openalex.org/W2889265484","https://openalex.org/W2951130829","https://openalex.org/W2952014059","https://openalex.org/W2952218014","https://openalex.org/W2973062255","https://openalex.org/W2974141411","https://openalex.org/W3015191643","https://openalex.org/W3019269619","https://openalex.org/W3093954063","https://openalex.org/W3096090308","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3111051109","https://openalex.org/W3112188842","https://openalex.org/W3126399577","https://openalex.org/W3163652268","https://openalex.org/W4367597591","https://openalex.org/W4384520820","https://openalex.org/W4392538456","https://openalex.org/W6703049675"],"related_works":["https://openalex.org/W4287179229","https://openalex.org/W3205513966","https://openalex.org/W3120459843","https://openalex.org/W4366547574","https://openalex.org/W3200191727","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117"],"abstract_inverted_index":{"With":[0],"current":[1],"state-of-the-art":[2],"(SOTA)":[3],"automatic":[4],"speech":[5,16,90,108,138,171,250],"recognition":[6],"(ASR)":[7],"systems,":[8],"it":[9,40,50,197],"is":[10,41,51],"not":[11],"possible":[12],"to":[13,44,59,103,134,163,195,217],"transcribe":[14],"overlapping":[15,136],"audio":[17,82,141,254],"streams":[18],"separately.":[19],"Consequently,":[20],"when":[21,239],"these":[22],"ASR":[23],"systems":[24,173],"are":[25],"used":[26],"as":[27,115,166,168],"part":[28],"of":[29,100,209,221],"a":[30,38,70,93,112,119,127,150,189,203,225],"social":[31,232],"robot":[32,106,191,233],"like":[33],"Pepper":[34],"for":[35,76,85,199],"interaction":[36,73],"with":[37],"human,":[39],"common":[42],"practice":[43],"close":[45],"the":[46,56,61,101,105,140,144,178,185,207,219,222,231,242,244,248,258],"robot\u2019s":[47,88],"microphone":[48],"while":[49],"talking":[52],"itself.":[53],"This":[54,96],"prevents":[55],"human":[57,137],"users":[58],"interrupt":[60,241],"robot,":[62,243],"which":[63,74],"limits":[64],"speech-based":[65],"human-robot":[66],"interaction.":[67],"To":[68],"enable":[69],"more":[71],"natural":[72],"allows":[75],"such":[77],"interruptions,":[78],"we":[79,154,213],"propose":[80],"an":[81],"processing":[83],"pipeline":[84,97,125,158,187,223,245],"filtering":[86],"out":[87],"ego":[89,107],"using":[91,230],"only":[92],"single-channel":[94,260],"microphone.":[95,146],"takes":[98],"advantage":[99],"possibility":[102],"feed":[104],"signal,":[109],"generated":[110],"by":[111,143,257],"text-to-speech":[113],"API,":[114],"training":[116],"data":[117],"into":[118,188],"machine":[120],"learning":[121],"model.":[122],"The":[123],"proposed":[124,186],"combines":[126],"convolutional":[128],"neural":[129],"network":[130],"and":[131],"spectral":[132],"subtraction":[133],"extract":[135,247],"from":[139,251],"recorded":[142],"robot-embedded":[145,259],"When":[147],"evaluating":[148],"on":[149,177],"held-out":[151],"test":[152],"set,":[153],"find":[155],"that":[156,174,238],"this":[157,164,215],"outperforms":[159],"our":[160,211],"previous":[161],"approach":[162],"task,":[165],"well":[167],"SOTA":[169],"target":[170],"extraction":[172],"were":[175],"retrained":[176],"same":[179],"dataset.":[180],"We":[181],"have":[182],"also":[183],"integrated":[184],"lightweight":[190],"software":[192],"development":[193],"framework":[194,216],"make":[196],"available":[198],"broader":[200],"use.":[201],"As":[202],"step":[204],"towards":[205],"demonstrating":[206],"feasibility":[208,228],"deploying":[210],"pipeline,":[212],"use":[214],"evaluate":[218],"effectiveness":[220],"in":[224,263],"small":[226],"lab-based":[227],"pilot":[229],"Pepper.":[234],"Our":[235],"results":[236],"show":[237],"participants":[240],"can":[246],"participant\u2019s":[249],"one-second":[252],"streaming":[253],"buffers":[255],"received":[256],"microphone,":[261],"hence":[262],"near-real":[264],"time.":[265]},"counts_by_year":[],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}