{"id":"https://openalex.org/W2150320044","doi":"https://doi.org/10.1109/roman.2007.4415208","title":"On-Line Speaker Enrollment using Rhythmical Voices for Human Robot Interaction","display_name":"On-Line Speaker Enrollment using Rhythmical Voices for Human Robot Interaction","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2150320044","doi":"https://doi.org/10.1109/roman.2007.4415208","mag":"2150320044"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2007.4415208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2007.4415208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication","raw_type":"proceedings-article"},"type":"article","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/A5022084872","display_name":"Kyung-Sook Bae","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kyungsook Bae","raw_affiliation_strings":["Intelligent Robot Research Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Intelligent Robot Research Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyejin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyejin Kim","raw_affiliation_strings":["Intelligent Robot Research Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Intelligent Robot Research Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080268629","display_name":"Keun-Chang Kwak","orcid":"https://orcid.org/0000-0002-3821-0711"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Keunchang Kwak","raw_affiliation_strings":["Intelligent Robot Research Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Intelligent Robot Research Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109172049","display_name":"Hosub Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hosub Yoon","raw_affiliation_strings":["Intelligent Robot Research Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Intelligent Robot Research Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022084872"],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12564621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"878","last_page":"881"},"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":0.9993000030517578,"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":0.996999979019165,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8497663736343384},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7254893183708191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7113476991653442},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6802549958229065},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6096274256706238},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6071416735649109},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5554036498069763},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5222350358963013},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5127952694892883},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.4925597310066223},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4725639224052429},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4417729675769806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.435324490070343},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4255688786506653},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.28985655307769775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09072133898735046},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06841441988945007}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8497663736343384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7254893183708191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113476991653442},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6802549958229065},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6096274256706238},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6071416735649109},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5554036498069763},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5222350358963013},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5127952694892883},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.4925597310066223},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4725639224052429},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4417729675769806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.435324490070343},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4255688786506653},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28985655307769775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09072133898735046},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06841441988945007},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/roman.2007.4415208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2007.4415208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1497065097","https://openalex.org/W1898362271","https://openalex.org/W2049633694","https://openalex.org/W2061013432","https://openalex.org/W2108168630","https://openalex.org/W2129244720","https://openalex.org/W2130418280","https://openalex.org/W2165880886","https://openalex.org/W2545131480","https://openalex.org/W6728846001"],"related_works":["https://openalex.org/W2048014685","https://openalex.org/W3009295899","https://openalex.org/W2370972896","https://openalex.org/W3119288895","https://openalex.org/W2128073728","https://openalex.org/W4234190324","https://openalex.org/W2185075503","https://openalex.org/W1197719229","https://openalex.org/W2129090883","https://openalex.org/W2972577568"],"abstract_inverted_index":{"In":[0],"this":[1,21],"study,":[2],"we":[3],"present":[4],"a":[5,32,59],"simple":[6,33],"on-line":[7],"speaker":[8,23,67],"enrollment":[9,24,41,105],"and":[10,79],"identification":[11],"among":[12],"human-robot":[13],"interaction":[14],"(HRI)":[15],"with":[16],"intelligent":[17],"service":[18],"robots.":[19],"For":[20],"purpose,":[22],"is":[25,69],"performed":[26],"through":[27],"rhythmical":[28],"singing":[29],"voices":[30],"or":[31],"game":[34],"such":[35],"as":[36],"paper-scissors-rock.":[37],"While":[38],"the":[39,46,52,65,73,89,99,103],"conventional":[40,104],"methods":[42],"frequently":[43],"used":[44],"in":[45,58,96],"security":[47],"area":[48],"should":[49],"be":[50,56],"cooperative,":[51],"proposed":[53,90],"approach":[54,91],"can":[55],"enrolled":[57],"very":[60],"natural":[61],"way.":[62],"After":[63],"enrolling,":[64],"text-independent":[66],"recognition":[68,94],"accomplished":[70],"by":[71,102],"using":[72],"well-known":[74],"mel-frequency":[75],"cepstral":[76],"coefficients":[77],"(MFCC)":[78],"Gaussian":[80],"mixture":[81],"models":[82],"(GMM).":[83],"The":[84],"experimental":[85],"results":[86,100],"reveal":[87],"that":[88],"yields":[92],"better":[93],"performance":[95],"comparison":[97],"to":[98],"obtained":[101],"method.":[106]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
