{"id":"https://openalex.org/W2020660155","doi":"https://doi.org/10.1109/iros.2014.6942735","title":"Speech-based human-robot interaction robust to acoustic reflections in real environment","display_name":"Speech-based human-robot interaction robust to acoustic reflections in real environment","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2020660155","doi":"https://doi.org/10.1109/iros.2014.6942735","mag":"2020660155"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2014.6942735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2014.6942735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE/RSJ International Conference on Intelligent Robots and Systems","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., Honcho Wako-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Ltd. Co., Honcho Wako-shi, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058775745","display_name":"Koji Inoue","orcid":"https://orcid.org/0000-0002-2929-2559"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koji Inoue","raw_affiliation_strings":["Kyoto University, Japan","Kyoto University Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"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., Honcho Wako-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Ltd. Co., Honcho 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., Honcho Wako-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Ltd. Co., Honcho 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., Honcho Wako-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Ltd. Co., Honcho Wako-shi, Japan","institution_ids":["https://openalex.org/I1283473643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1367","last_page":"1373"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7453511357307434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7014524936676025},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6830846667289734},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.6773858666419983},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5425399541854858},{"id":"https://openalex.org/keywords/imaging-phantom","display_name":"Imaging phantom","score":0.5191051959991455},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4762318730354309},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4360232353210449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37236544489860535},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07481077313423157}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7453511357307434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7014524936676025},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6830846667289734},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.6773858666419983},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5425399541854858},{"id":"https://openalex.org/C104293457","wikidata":"https://www.wikidata.org/wiki/Q28324852","display_name":"Imaging phantom","level":2,"score":0.5191051959991455},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4762318730354309},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4360232353210449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37236544489860535},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07481077313423157},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/iros.2014.6942735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2014.6942735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1512562331","https://openalex.org/W2017519504","https://openalex.org/W2053241019","https://openalex.org/W2069432516","https://openalex.org/W2102072896","https://openalex.org/W2104422351","https://openalex.org/W2106259503","https://openalex.org/W2113416157","https://openalex.org/W2121065047","https://openalex.org/W2128653836","https://openalex.org/W2136197758","https://openalex.org/W2152949589","https://openalex.org/W2172226263","https://openalex.org/W2911394281","https://openalex.org/W3143675102","https://openalex.org/W4230562743","https://openalex.org/W6678139903","https://openalex.org/W6680064849","https://openalex.org/W6682371270","https://openalex.org/W6758139422"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W4287179229","https://openalex.org/W3205513966","https://openalex.org/W3120459843","https://openalex.org/W4366547574","https://openalex.org/W3200191727"],"abstract_inverted_index":{"Acoustic":[0],"reflection":[1,53,86],"inside":[2],"an":[3],"enclosed":[4],"environment":[5],"is":[6,113,119,149,189],"detrimental":[7],"to":[8,32,41,47,60,84,90,104,121,151,169,191],"human-robot":[9,94,101,206],"interaction.":[10,95],"Reflection":[11],"may":[12,26],"manifest":[13,28],"as":[14,29,186],"phantom":[15,178,187],"sources":[16,179],"emanating":[17],"from":[18,177],"unknown":[19],"directions.":[20],"In":[21],"effect,":[22],"a":[23,98,131,137,165],"single":[24],"speaker":[25],"falsely":[27],"multiple":[30],"speakers":[31],"the":[33,38,44,48,55,91,105,123,127,146,158,172,182,193,211,215],"robot":[34,70],"audition":[35,71],"system,":[36],"impeding":[37],"robot's":[39],"ability":[40],"correctly":[42],"associate":[43],"speech":[45,52,57,64,153,200],"command":[46],"actual":[49],"speaker.":[50],"Moreover,":[51],"smears":[54],"original":[56,173],"signal":[58],"due":[59],"reverberation.":[61],"This":[62],"degrades":[63],"recognition":[65],"and":[66,78,115,143],"understanding":[67],"performance.":[68],"Conventional":[69],"schemes":[72],"that":[73],"rely":[74],"purely":[75],"on":[76],"acoustics":[77],"spatial":[79],"information":[80,112,125,148,159],"are":[81,203],"very":[82],"sensitive":[83],"acoustic":[85,108,124,147],"which":[87,210],"ultimately":[88],"leads":[89],"failure":[92],"in":[93,205,209],"We":[96],"propose":[97],"method":[99,213],"for":[100,196],"interaction":[102,207],"robust":[103],"effect":[106],"of":[107,130],"reflection.":[109],"First,":[110],"visual":[111,128],"utilized":[114],"head":[116],"tracking":[117],"scheme":[118,142],"employed":[120],"reinforce":[122],"with":[126],"presence":[129],"prospect":[132],"user.":[133],"Second,":[134],"we":[135,160,163],"employ":[136],"model-based":[138],"sound":[139],"event":[140],"identification":[141],"scrutinize":[144],"whether":[145],"likely":[150],"be":[152],"or":[154],"non-speech.":[155],"Using":[156],"all":[157],"have":[161],"gathered,":[162],"create":[164],"simple":[166],"rule":[167],"construct":[168],"effectively":[170],"discriminate":[171],"source":[174,184],"(actual":[175],"speaker)":[176],"(reflection).":[180],"Consequently,":[181],"corresponding":[183],"identified":[185],"(reflection)":[188],"used":[190],"estimate":[192],"unwanted":[194],"smearing":[195],"effective":[197],"suppression":[198],"via":[199],"enhancement.":[201],"Experiments":[202],"conducted":[204],"setting":[208],"proposed":[212],"outperforms":[214],"conventional":[216],"method.":[217]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
