{"id":"https://openalex.org/W4224918587","doi":"https://doi.org/10.1109/icassp43922.2022.9747048","title":"Modeling Beats and Downbeats with a Time-Frequency Transformer","display_name":"Modeling Beats and Downbeats with a Time-Frequency Transformer","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224918587","doi":"https://doi.org/10.1109/icassp43922.2022.9747048"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747048","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5005504900","display_name":"Yun-Ning Hung","orcid":"https://orcid.org/0000-0002-7242-6903"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun-Ning Hung","raw_affiliation_strings":["Georgia Institute of Technology,Center for Music Technology,Atlanta,GA,USA","Center for Music Technology, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Center for Music Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Music Technology, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[{"id":"https://openalex.org/I2800240351","display_name":"Mountain View College","ror":"https://ror.org/04fh8an03","country_code":"US","type":"education","lineage":["https://openalex.org/I1291072267","https://openalex.org/I2800240351"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["ByteDance,Mountain View,CA,USA","ByteDance, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Mountain View,CA,USA","institution_ids":["https://openalex.org/I2800240351"]},{"raw_affiliation_string":"ByteDance, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104098658","display_name":"Xuchen Song","orcid":null},"institutions":[{"id":"https://openalex.org/I2800240351","display_name":"Mountain View College","ror":"https://ror.org/04fh8an03","country_code":"US","type":"education","lineage":["https://openalex.org/I1291072267","https://openalex.org/I2800240351"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuchen Song","raw_affiliation_strings":["ByteDance,Mountain View,CA,USA","ByteDance, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Mountain View,CA,USA","institution_ids":["https://openalex.org/I2800240351"]},{"raw_affiliation_string":"ByteDance, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070642261","display_name":"Wei-Tsung Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I2800240351","display_name":"Mountain View College","ror":"https://ror.org/04fh8an03","country_code":"US","type":"education","lineage":["https://openalex.org/I1291072267","https://openalex.org/I2800240351"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Tsung Lu","raw_affiliation_strings":["ByteDance,Mountain View,CA,USA","ByteDance, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Mountain View,CA,USA","institution_ids":["https://openalex.org/I2800240351"]},{"raw_affiliation_string":"ByteDance, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041096205","display_name":"Minz Won","orcid":"https://orcid.org/0000-0002-6921-1733"},"institutions":[{"id":"https://openalex.org/I2800240351","display_name":"Mountain View College","ror":"https://ror.org/04fh8an03","country_code":"US","type":"education","lineage":["https://openalex.org/I1291072267","https://openalex.org/I2800240351"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minz Won","raw_affiliation_strings":["ByteDance,Mountain View,CA,USA","ByteDance, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Mountain View,CA,USA","institution_ids":["https://openalex.org/I2800240351"]},{"raw_affiliation_string":"ByteDance, Mountain View, CA, USA","institution_ids":[]}]}],"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":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7002488374710083},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6603362560272217},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5790547728538513},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5033401846885681},{"id":"https://openalex.org/keywords/beat","display_name":"Beat (acoustics)","score":0.4597371816635132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3614081144332886},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18007415533065796},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16667777299880981},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1305992305278778},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07235541939735413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002488374710083},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6603362560272217},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5790547728538513},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5033401846885681},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.4597371816635132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3614081144332886},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18007415533065796},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16667777299880981},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1305992305278778},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07235541939735413},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747048","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1519655822","https://openalex.org/W1522301498","https://openalex.org/W1602172476","https://openalex.org/W1999949665","https://openalex.org/W2016885049","https://openalex.org/W2114640443","https://openalex.org/W2142455137","https://openalex.org/W2155764689","https://openalex.org/W2156063659","https://openalex.org/W2167455298","https://openalex.org/W2170678332","https://openalex.org/W2295819747","https://openalex.org/W2302255633","https://openalex.org/W2350911425","https://openalex.org/W2402118560","https://openalex.org/W2404176928","https://openalex.org/W2404509795","https://openalex.org/W2405656250","https://openalex.org/W2407685581","https://openalex.org/W2572771584","https://openalex.org/W2896457183","https://openalex.org/W2902458379","https://openalex.org/W2936217452","https://openalex.org/W2952395326","https://openalex.org/W2984379537","https://openalex.org/W2989608619","https://openalex.org/W2990861008","https://openalex.org/W2991377373","https://openalex.org/W3015289235","https://openalex.org/W3118825798","https://openalex.org/W3207444892","https://openalex.org/W4224944643","https://openalex.org/W4286850225","https://openalex.org/W4288287237","https://openalex.org/W4310304411","https://openalex.org/W4385245566","https://openalex.org/W6631117800","https://openalex.org/W6631190155","https://openalex.org/W6636237774","https://openalex.org/W6697467378","https://openalex.org/W6698183232","https://openalex.org/W6713329139","https://openalex.org/W6714030504","https://openalex.org/W6739901393","https://openalex.org/W6740984418","https://openalex.org/W6755207826","https://openalex.org/W6756479656","https://openalex.org/W6764574124","https://openalex.org/W6765005523","https://openalex.org/W6770646036","https://openalex.org/W6771230977","https://openalex.org/W6803003856","https://openalex.org/W6803752119","https://openalex.org/W6941176339"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2119949815"],"abstract_inverted_index":{"Transformer":[0,48,54,84],"is":[1],"a":[2,32,51,63,73,151],"successful":[3],"deep":[4],"neural":[5],"network":[6],"(DNN)":[7],"architecture":[8,146],"that":[9,55,147,167],"has":[10],"shown":[11],"its":[12],"versatility":[13],"not":[14],"only":[15],"in":[16,22,49,174,181],"natural":[17],"language":[18],"processing":[19],"but":[20],"also":[21,143],"music":[23,67],"information":[24,135],"retrieval":[25],"(MIR).":[26],"In":[27],"this":[28,120],"paper,":[29],"we":[30],"present":[31],"novel":[33],"Transformer-based":[34],"approach":[35,43,169],"to":[36,99,102,136,139,159],"tackle":[37],"beat":[38,182],"and":[39,59,95,113],"downbeat":[40,124,175],"tracking.":[41,183],"This":[42],"employs":[44],"SpecTNT":[45,70,149],"(Spectral-":[46],"Temporal":[47,155],"Transformer),":[50],"variant":[52],"of":[53,62,66,75,80,83,105],"models":[56],"both":[57],"spectral":[58,93,134],"temporal":[60],"dimensions":[61],"time-frequency":[64],"input":[65],"audio.":[68],"A":[69],"model":[71,98],"uses":[72],"stack":[74],"blocks,":[76],"where":[77],"each":[78,106],"consists":[79],"two":[81],"levels":[82],"encoders.":[85],"The":[86,126],"lower-level":[87],"(or":[88,128],"spectral)":[89],"encoder":[90,130],"handles":[91],"the":[92,97,162],"features":[94],"enables":[96],"pay":[100,137],"attention":[101,138],"harmonic":[103,118],"components":[104],"frame.":[107],"Since":[108],"downbeats":[109],"indicate":[110],"bar":[111],"boundaries":[112],"are":[114],"often":[115],"accompanied":[116],"by":[117],"changes,":[119],"step":[121],"may":[122],"help":[123],"modeling.":[125],"upper-level":[127],"temporal)":[129],"aggregates":[131],"useful":[132],"local":[133],"beat/downbeat":[140],"positions.":[141],"We":[142],"propose":[144],"an":[145],"combines":[148],"with":[150],"state-of-":[152],"the-art":[153],"model,":[154],"Convolutional":[156],"Networks":[157],"(TCN),":[158],"further":[160],"improve":[161],"performance.":[163],"Extensive":[164],"experiments":[165],"demonstrate":[166],"our":[168],"can":[170],"significantly":[171],"outperform":[172],"TCN":[173],"tracking":[176],"while":[177],"maintaining":[178],"comparable":[179],"result":[180]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}