{"id":"https://openalex.org/W4372260062","doi":"https://doi.org/10.1109/icassp49357.2023.10095390","title":"RAT: Radial Attention Transformer for Singing Technique Recognition","display_name":"RAT: Radial Attention Transformer for Singing Technique Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260062","doi":"https://doi.org/10.1109/icassp49357.2023.10095390"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095390","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103188965","display_name":"Guan-Yuan Chen","orcid":"https://orcid.org/0000-0003-3298-0624"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]},{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Guan-Yuan Chen","raw_affiliation_strings":["National Tsing Hua University","Chunghwa Telecom Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Chunghwa Telecom Laboratories","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031808295","display_name":"Ya-Fen Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I142066694","display_name":"ITRI International","ror":"https://ror.org/04wwsbd59","country_code":"US","type":"facility","lineage":["https://openalex.org/I142066694"]},{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Ya-Fen Yeh","raw_affiliation_strings":["National Tsing Hua University","Industrial Technology Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Industrial Technology Research Institute","institution_ids":["https://openalex.org/I142066694"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080558475","display_name":"Von\u2010Wun Soo","orcid":"https://orcid.org/0000-0002-4810-1244"},"institutions":[{"id":"https://openalex.org/I173093425","display_name":"Chang Gung University","ror":"https://ror.org/00d80zx46","country_code":"TW","type":"education","lineage":["https://openalex.org/I173093425"]},{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Von-Wun Soo","raw_affiliation_strings":["National Tsing Hua University","Chang Gung University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Chang Gung University","institution_ids":["https://openalex.org/I173093425"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0324508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8952676057815552},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8270784616470337},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7619110345840454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6936326622962952},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.6268742084503174},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5709131360054016},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.46502161026000977},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4218778908252716},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4105511009693146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40620625019073486},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.24773922562599182},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.13346120715141296},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12749126553535461},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08684071898460388}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8952676057815552},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8270784616470337},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7619110345840454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6936326622962952},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.6268742084503174},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5709131360054016},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.46502161026000977},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4218778908252716},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4105511009693146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40620625019073486},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.24773922562599182},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.13346120715141296},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12749126553535461},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08684071898460388},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095390","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2903032817","https://openalex.org/W2962772649","https://openalex.org/W2963418739","https://openalex.org/W2969985801","https://openalex.org/W2995197345","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W3144810982","https://openalex.org/W3201565470","https://openalex.org/W4283652003","https://openalex.org/W4298187611","https://openalex.org/W4385245566","https://openalex.org/W4386075553","https://openalex.org/W6739901393","https://openalex.org/W6749046737","https://openalex.org/W6757202746","https://openalex.org/W6768920361","https://openalex.org/W6784333009","https://openalex.org/W6810607895","https://openalex.org/W6844051892"],"related_works":["https://openalex.org/W2373880408","https://openalex.org/W1107690805","https://openalex.org/W405661683","https://openalex.org/W2532856746","https://openalex.org/W2097318409","https://openalex.org/W238390473","https://openalex.org/W2739662815","https://openalex.org/W4288088492","https://openalex.org/W2982290989","https://openalex.org/W4394924759"],"abstract_inverted_index":{"Singing":[0],"techniques":[1,27,55],"are":[2,39],"important":[3],"skills":[4],"for":[5],"a":[6,46,87,94],"professional":[7],"vocal":[8],"performance":[9],"that":[10,42,99,120],"usually":[11],"involves":[12],"dedicated":[13],"fluctuations":[14],"of":[15,25,49,72,113,146],"timbre,":[16],"pitch,":[17],"duration,":[18],"and":[19,59,139],"loudness,":[20],"etc.":[21],"To":[22,81],"recognize":[23],"types":[24],"singing":[26,38,54,73,147],"can":[28,100],"be":[29],"quite":[30],"challenging":[31],"because":[32],"1)":[33],"the":[34,67,78,102,109,121,143],"time-frequency":[35],"features":[36,65,105],"in":[37,45,66],"highly":[40],"dynamic":[41],"may":[43],"appear":[44],"long":[47,110],"range":[48,111],"audio":[50,114],"signals;":[51],"2)":[52],"different":[53],"such":[56],"as":[57,106,108],"vibrato":[58],"trill":[60],"tend":[61],"to":[62],"have":[63],"similar":[64],"locality;":[68],"3)":[69],"The":[70,116],"distribution":[71],"technique":[74,148],"dataset":[75],"suffers":[76],"from":[77],"long-tailed":[79],"issue.":[80],"man-age":[82],"these":[83],"problems,":[84],"we":[85],"proposed":[86,122],"novel":[88],"Radial":[89,95],"Attention":[90,96],"Transformer":[91],"(RAT)":[92],"with":[93,125],"(RA)":[97],"Module":[98],"capture":[101],"fine-grained":[103],"local":[104],"well":[107],"inter-dependency":[112],"features.":[115],"experiment":[117],"results":[118],"showed":[119],"method,":[123],"RAT":[124],"Adaptive":[126],"Logit":[127],"Adjustment":[128],"(ALA)":[129],"Loss":[130],"significantly":[131],"outperformed":[132],"pre-vious":[133],"state-of-the-art":[134],"models":[135],"(Convolutional":[136],"Neural":[137],"Networks":[138],"Deformable":[140],"CNN),":[141],"on":[142],"recognition":[144],"tasks":[145],"categories.":[149]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
