{"id":"https://openalex.org/W4392910539","doi":"https://doi.org/10.1109/icassp48485.2024.10446611","title":"Beast: Online Joint Beat and Downbeat Tracking Based on Streaming Transformer","display_name":"Beast: Online Joint Beat and Downbeat Tracking Based on Streaming Transformer","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910539","doi":"https://doi.org/10.1109/icassp48485.2024.10446611"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5071072116","display_name":"Chih-Cheng Chang","orcid":"https://orcid.org/0000-0002-5517-5065"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chih-Cheng Chang","raw_affiliation_strings":["Academia Sinica,Institute of Information Science,Taipei,Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Institute of Information Science,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038264558","display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4275-8832"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["Academia Sinica,Institute of Information Science,Taipei,Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Institute of Information Science,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071072116"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65504872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"396","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8970000147819519,"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/T10860","display_name":"Speech and Audio Processing","score":0.8970000147819519,"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":0.8644999861717224,"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":0.8014000058174133,"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":0.6491799354553223},{"id":"https://openalex.org/keywords/beat","display_name":"Beat (acoustics)","score":0.5817298889160156},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4798666834831238},{"id":"https://openalex.org/keywords/video-streaming","display_name":"Video streaming","score":0.42808443307876587},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.41490787267684937},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3261410593986511},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.312495619058609},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.17753982543945312},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13691246509552002},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12316867709159851}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6491799354553223},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.5817298889160156},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4798666834831238},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.42808443307876587},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.41490787267684937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3261410593986511},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.312495619058609},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.17753982543945312},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13691246509552002},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12316867709159851},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural 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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":25,"referenced_works":["https://openalex.org/W75292264","https://openalex.org/W2016885049","https://openalex.org/W2058715312","https://openalex.org/W2156063659","https://openalex.org/W2402118560","https://openalex.org/W2405656250","https://openalex.org/W2909193097","https://openalex.org/W2913718171","https://openalex.org/W2936217452","https://openalex.org/W2963925437","https://openalex.org/W2964110616","https://openalex.org/W3007433671","https://openalex.org/W3096888553","https://openalex.org/W3118825798","https://openalex.org/W3170881237","https://openalex.org/W4224918587","https://openalex.org/W4281667020","https://openalex.org/W4310304411","https://openalex.org/W4385245566","https://openalex.org/W6640055364","https://openalex.org/W6713329139","https://openalex.org/W6740984418","https://openalex.org/W6755406732","https://openalex.org/W6846277122","https://openalex.org/W6941176339"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2090102624","https://openalex.org/W2888483922","https://openalex.org/W1490229056","https://openalex.org/W2009462014","https://openalex.org/W653810948","https://openalex.org/W4205930110","https://openalex.org/W4396737233","https://openalex.org/W2367747139"],"abstract_inverted_index":{"Many":[0],"deep":[1],"learning":[2],"models":[3],"have":[4],"achieved":[5],"dominant":[6],"performance":[7],"on":[8,51,102],"the":[9,21,52,66,76,80,141],"offline":[10],"beat":[11,16,45,98,123,144],"tracking":[12,38,48,147],"task.":[13],"However,":[14],"online":[15,43,58,143],"tracking,":[17],"in":[18,65,75,94,122,126],"which":[19,89,128],"only":[20],"past":[22],"and":[23,46,99,124,136,145],"present":[24],"input":[25],"features":[26],"are":[27],"available,":[28],"still":[29],"remains":[30],"challenging.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,70],"propose":[36],"BEAt":[37],"Streaming":[39],"Transformer":[40,67,82],"(BEAST),":[41],"an":[42,118],"joint":[44],"downbeat":[47,100,146],"system":[49],"based":[50],"streaming":[53,81],"Transformer.":[54],"To":[55],"deal":[56],"with":[57,110],"scenarios,":[59],"BEAST":[60,116],"applies":[61],"contextual":[62],"block":[63],"processing":[64],"encoder.":[68],"Moreover,":[69],"adopt":[71],"relative":[72,86],"positional":[73],"encoding":[74],"attention":[77],"layer":[78],"of":[79,120,133],"encoder":[83],"to":[84],"capture":[85],"timing":[87],"position":[88],"is":[90,129],"critically":[91],"important":[92],"information":[93],"music.":[95],"Carrying":[96],"out":[97],"experiments":[101],"benchmark":[103],"datasets":[104],"for":[105],"a":[106,130],"low":[107],"latency":[108,112],"scenario":[109],"maximum":[111],"under":[113],"50":[114],"ms,":[115],"achieves":[117],"F1-measure":[119],"80.04%":[121],"52.73%":[125],"downbeat,":[127],"substantial":[131],"improvement":[132],"about":[134],"5":[135],"13":[137],"percentage":[138],"points":[139],"over":[140],"state-of-the-art":[142],"model.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
