{"id":"https://openalex.org/W4404953589","doi":"https://doi.org/10.1109/humanoids58906.2024.10769827","title":"Learning Tone: Towards Robotic Xylophone Mastery","display_name":"Learning Tone: Towards Robotic Xylophone Mastery","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4404953589","doi":"https://doi.org/10.1109/humanoids58906.2024.10769827"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids58906.2024.10769827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids58906.2024.10769827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE-RAS 23rd 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/A5100462810","display_name":"Jiawei Zhang","orcid":"https://orcid.org/0000-0001-5248-4949"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Zhang","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Urbana,IL,USA,61801"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Urbana,IL,USA,61801","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026355028","display_name":"Taemoon Jeong","orcid":"https://orcid.org/0009-0003-8675-4064"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taemoon Jeong","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092612129","display_name":"Sankalp Yamsani","orcid":"https://orcid.org/0000-0002-5590-1792"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sankalp Yamsani","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Urbana,IL,USA,61801"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Urbana,IL,USA,61801","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047885515","display_name":"Sungjoon Choi","orcid":"https://orcid.org/0000-0002-3049-8212"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungjoon Choi","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089263869","display_name":"Joohyung Kim","orcid":"https://orcid.org/0000-0001-9575-2835"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joohyung Kim","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Urbana,IL,USA,61801"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Urbana,IL,USA,61801","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"221","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9703999757766724,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9564999938011169,"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":0.7793434858322144},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7623798847198486},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.6508760452270508},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5830011963844299},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4757154583930969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4683398902416229},{"id":"https://openalex.org/keywords/audio-feedback","display_name":"Audio feedback","score":0.44536298513412476},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39078572392463684},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17705339193344116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793434858322144},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7623798847198486},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.6508760452270508},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5830011963844299},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4757154583930969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4683398902416229},{"id":"https://openalex.org/C38956757","wikidata":"https://www.wikidata.org/wiki/Q716215","display_name":"Audio feedback","level":2,"score":0.44536298513412476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39078572392463684},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17705339193344116},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids58906.2024.10769827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids58906.2024.10769827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2076052312","https://openalex.org/W2144994235","https://openalex.org/W2158782408","https://openalex.org/W2210408922","https://openalex.org/W2963411833","https://openalex.org/W2968340082","https://openalex.org/W2990747716","https://openalex.org/W3113172960","https://openalex.org/W4281887079","https://openalex.org/W4385656358","https://openalex.org/W4390480932","https://openalex.org/W4401416238","https://openalex.org/W6627932998","https://openalex.org/W6646978632","https://openalex.org/W6729653997","https://openalex.org/W6741002519","https://openalex.org/W6782754186","https://openalex.org/W6800004206","https://openalex.org/W6803178138","https://openalex.org/W6804601995","https://openalex.org/W6845296567","https://openalex.org/W6850231670","https://openalex.org/W6851774385","https://openalex.org/W6870422567","https://openalex.org/W6875452911"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2176409448","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2538520412","https://openalex.org/W2883092465"],"abstract_inverted_index":{"Audio":[0],"information":[1],"plays":[2],"an":[3,24],"important":[4],"role":[5],"in":[6,35,52,62,85],"various":[7],"robotic":[8],"manipulation":[9],"tasks,":[10],"such":[11],"as":[12,17,23,58,107],"pouring":[13],"and":[14,111],"music":[15],"performance,":[16],"the":[18,41,83,86,91,96,102,105],"produced":[19,97],"audio":[20,45,73],"can":[21,100],"serve":[22],"informative":[25],"indicator":[26],"for":[27],"evaluating":[28],"actions.":[29],"However,":[30],"it":[31,47,57],"is":[32,48],"rarely":[33],"explored":[34],"reinforcement":[36,68],"learning":[37,69],"methods.":[38],"Due":[39],"to":[40,50,76,81,113],"unique":[42],"nature":[43],"of":[44,104],"information,":[46],"challenging":[49],"simulate":[51],"a":[53,67,78],"simulator":[54],"or":[55],"use":[56],"direct":[59],"feedback.":[60],"Therefore,":[61],"this":[63],"paper,":[64],"we":[65,99],"propose":[66],"method":[70],"based":[71],"on":[72],"feedback,":[74],"aiming":[75],"train":[77],"dexterous":[79,92],"hand":[80],"play":[82],"xylophone":[84],"real":[87],"world.":[88],"By":[89],"optimizing":[90],"hand\u2019s":[93],"actions":[94],"using":[95],"audio,":[98],"make":[101],"characteristics":[103],"audio-\u2014such":[106],"amplitude,":[108],"waveform":[109],"shape,":[110],"timing\u2014similar":[112],"human":[114],"performance.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
