{"id":"https://openalex.org/W2556829066","doi":"https://doi.org/10.1109/roman.2016.7745087","title":"Leveraging phantom signals for improved voice-based human-robot interaction","display_name":"Leveraging phantom signals for improved voice-based human-robot interaction","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2556829066","doi":"https://doi.org/10.1109/roman.2016.7745087","mag":"2556829066"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2016.7745087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2016.7745087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","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/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["Honda Research Institute Japan Ltd. Co., Wako-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Ltd. Co., Wako-shi, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052659556","display_name":"Yurii Vasylkiv","orcid":"https://orcid.org/0000-0003-3603-1645"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yurii Vasylkiv","raw_affiliation_strings":["Honda Research Institute Japan Ltd. Co., Wako-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Ltd. Co., Wako-shi, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049329632","display_name":"Keisuke Nakamura","orcid":"https://orcid.org/0000-0002-4979-2083"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Nakamura","raw_affiliation_strings":["Honda Research Institute Japan Ltd. Co., Wako-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Ltd. Co., Wako-shi, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110835440","display_name":"Takeshi Mizumoto","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Mizumoto","raw_affiliation_strings":["Honda Research Institute Japan Ltd. Co., Wako-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Ltd. Co., Wako-shi, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Honda Research Institute Japan Ltd. Co., Wako-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Ltd. Co., Wako-shi, Japan","institution_ids":["https://openalex.org/I1283473643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1283473643"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"30","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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":0.7918537855148315},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.732245683670044},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6507068276405334},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6205488443374634},{"id":"https://openalex.org/keywords/imaging-phantom","display_name":"Imaging phantom","score":0.5291255712509155},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4685417413711548},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4587422311306},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.45852819085121155},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.4287633001804352},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4171903431415558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3769153654575348},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33665427565574646},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08365949988365173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918537855148315},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.732245683670044},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6507068276405334},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6205488443374634},{"id":"https://openalex.org/C104293457","wikidata":"https://www.wikidata.org/wiki/Q28324852","display_name":"Imaging phantom","level":2,"score":0.5291255712509155},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4685417413711548},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4587422311306},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.45852819085121155},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.4287633001804352},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4171903431415558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3769153654575348},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33665427565574646},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08365949988365173},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/roman.2016.7745087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2016.7745087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W82800962","https://openalex.org/W1487851247","https://openalex.org/W2009106392","https://openalex.org/W2016565202","https://openalex.org/W2037740282","https://openalex.org/W2100969003","https://openalex.org/W2102072896","https://openalex.org/W2113638573","https://openalex.org/W2115243148","https://openalex.org/W2122272452","https://openalex.org/W2133668545","https://openalex.org/W2141418660","https://openalex.org/W2144155486","https://openalex.org/W2146871184","https://openalex.org/W2147583357","https://openalex.org/W2152321507","https://openalex.org/W2168856390","https://openalex.org/W2197846949","https://openalex.org/W2207851367","https://openalex.org/W2396969243","https://openalex.org/W2606817353","https://openalex.org/W2759056399","https://openalex.org/W2900355250","https://openalex.org/W6603434965","https://openalex.org/W6677591520","https://openalex.org/W6712502737","https://openalex.org/W6744551257","https://openalex.org/W6756176664"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W4240587264","https://openalex.org/W2900122540","https://openalex.org/W2963983801","https://openalex.org/W3119734852","https://openalex.org/W2804363668","https://openalex.org/W1515932869","https://openalex.org/W2043735059"],"abstract_inverted_index":{"Voice-based":[0],"system":[1,151],"used":[2],"in":[3,29,57,113],"human-robot":[4],"interaction":[5],"is":[6,19,27,100],"susceptible":[7],"to":[8,48,81,94,102,166],"challenging":[9],"environment":[10],"conditions.":[11],"In":[12,117],"an":[13],"enclosed":[14],"environment,":[15],"the":[16,30,37,41,45,88,108,154,162,168,173],"speech":[17,133],"signal":[18],"often":[20],"reflected":[21],"which":[22],"causes":[23],"smearing":[24],"as":[25],"it":[26],"observed":[28,155],"microphone.":[31],"This":[32],"phenomenon":[33],"creates":[34],"mismatch":[35],"with":[36,135],"acoustic":[38],"model,":[39],"degrading":[40],"recognition":[42],"performance":[43],"and":[44,50,67,107,138,159],"robot's":[46,58],"ability":[47],"understand":[49],"execute":[51],"commands.":[52],"Moreover,":[53],"phantoms":[54,158],"increase":[55],"false-alarm":[56],"attention":[59],"system.":[60],"To":[61],"address":[62],"these":[63,127],"issues,":[64],"environment-matched":[65],"training":[66,79],"model":[68,140,163],"adaptation":[69,92],"may":[70],"be":[71,95],"used.":[72],"The":[73],"former":[74],"requires":[75],"enormous":[76],"amount":[77],"of":[78],"data":[80,93,105],"exhaustively":[82],"cover":[83],"different":[84],"matched":[85],"conditions":[86],"whereas":[87],"latter":[89],"needs":[90],"several":[91],"collected":[96],"at":[97,164],"runtime.":[98],"It":[99],"important":[101],"stress":[103],"that":[104,125,152,172],"collection":[106],"wait":[109],"time":[110],"are":[111],"luxuries":[112],"a":[114,144,148],"robot":[115],"setup.":[116],"this":[118],"paper,":[119],"we":[120,146],"extend":[121],"our":[122,178],"previous":[123,179],"work":[124],"mitigates":[126],"problem":[128],"by":[129],"combining":[130],"environment-adaptive":[131],"training,":[132],"enhancement":[134],"phantom":[136],"awareness":[137],"fast":[139],"update,":[141],"respectively.":[142],"As":[143],"result,":[145],"achieve":[147],"robust":[149],"voice-based":[150],"enhances":[153],"speech,":[156],"rejects":[157],"automatically":[160],"updates":[161],"runtime":[165],"minimize":[167],"mismatch.":[169],"Results":[170],"show":[171],"proposed":[174],"method":[175],"significantly":[176],"outperforms":[177],"work.":[180]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
