{"id":"https://openalex.org/W2197846949","doi":"https://doi.org/10.1109/humanoids.2015.7363488","title":"Compensating changes in speaker position for improved voice-based human-robot communication","display_name":"Compensating changes in speaker position for improved voice-based human-robot communication","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2197846949","doi":"https://doi.org/10.1109/humanoids.2015.7363488","mag":"2197846949"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2015.7363488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2015.7363488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","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/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":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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"977","last_page":"982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7832649946212769},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7308427095413208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6322293877601624},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5830385088920593},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5797573328018188},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.492301344871521},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4128551483154297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3517691493034363},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3399239182472229},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12216532230377197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832649946212769},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7308427095413208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6322293877601624},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5830385088920593},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5797573328018188},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.492301344871521},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4128551483154297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3517691493034363},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3399239182472229},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12216532230377197},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids.2015.7363488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2015.7363488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","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":34,"referenced_works":["https://openalex.org/W82800962","https://openalex.org/W112202508","https://openalex.org/W113845259","https://openalex.org/W207188544","https://openalex.org/W1546395807","https://openalex.org/W1563101474","https://openalex.org/W1963844140","https://openalex.org/W2009106392","https://openalex.org/W2016565202","https://openalex.org/W2017519504","https://openalex.org/W2037740282","https://openalex.org/W2053241019","https://openalex.org/W2100969003","https://openalex.org/W2102072896","https://openalex.org/W2104690216","https://openalex.org/W2106259503","https://openalex.org/W2121065047","https://openalex.org/W2121788372","https://openalex.org/W2128847674","https://openalex.org/W2136197758","https://openalex.org/W2141418660","https://openalex.org/W2144155486","https://openalex.org/W2146871184","https://openalex.org/W2151046798","https://openalex.org/W2759056399","https://openalex.org/W2900355250","https://openalex.org/W6603434965","https://openalex.org/W6604438726","https://openalex.org/W6604658791","https://openalex.org/W6633775064","https://openalex.org/W6678139903","https://openalex.org/W6680064849","https://openalex.org/W6744551257","https://openalex.org/W6756176664"],"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],"perturbation":[1],"due":[2],"to":[3,13,59,77,127],"reverberation":[4],"and":[5,29,44,104,117],"the":[6,23,30,36,39,45,56,61,96,105,121,125],"changes":[7],"in":[8,82,107,129,140],"speaker":[9],"position":[10],"are":[11],"detrimental":[12],"seamless":[14],"human-robot":[15,80],"speech-based":[16,79],"communication.":[17],"These":[18],"cause":[19],"a":[20,54,75,100,108],"mismatch":[21,97,131],"between":[22,102],"speech":[24],"features":[25],"at":[26],"runtime":[27],"condition":[28],"acoustic":[31],"model":[32],"(training":[33],"condition).":[34],"Then":[35],"degradation":[37],"of":[38],"Automatic":[40],"Speech":[41],"Recognition":[42],"(ASR)":[43],"Spoken":[46],"Language":[47],"Understanding":[48],"(SLU)":[49],"performances":[50],"is":[51,88],"imminent.":[52],"As":[53],"consequence,":[55],"robot":[57,92,110],"fails":[58],"understand":[60],"spoken":[62],"commands":[63],"which":[64],"will":[65],"negatively":[66],"impact":[67],"interaction":[68],"experience.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"framework":[76,87,123],"improving":[78],"communication":[81],"various":[83],"reverberant":[84],"environments.":[85],"The":[86],"based":[89],"on":[90],"robust":[91],"audition":[93],"that":[94],"addresses":[95],"problem,":[98],"striking":[99],"balance":[101],"technology":[103],"limitations":[106],"real":[109,141],"setting.":[111],"Our":[112],"method":[113],"improves":[114],"both":[115],"ASR":[116],"SLU":[118],"performances.":[119],"Moreover,":[120],"proposed":[122],"has":[124],"ability":[126],"evolve":[128],"minimizing":[130],"without":[132],"human":[133],"supervision.":[134],"We":[135],"experiment":[136],"with":[137],"data":[138],"collected":[139],"environment":[142],"conditions.":[143]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}