{"id":"https://openalex.org/W2162948918","doi":"https://doi.org/10.1109/icassp.2012.6287821","title":"Playing with tagging: A real-time tagging music player","display_name":"Playing with tagging: A real-time tagging music player","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2162948918","doi":"https://doi.org/10.1109/icassp.2012.6287821","mag":"2162948918"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6287821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"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":"Ju-Chiang Wang","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"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":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"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/A5028285867","display_name":"Shyh\u2010Kang Jeng","orcid":"https://orcid.org/0000-0001-8960-9995"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shyh-Kang Jeng","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065288078"],"corresponding_institution_ids":["https://openalex.org/I16733864","https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":1.7335,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88279522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"80"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9977999925613403,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8242789506912231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6607316136360168},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.6260080337524414},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5949521064758301},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.504491925239563},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.41880717873573303},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4148402810096741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3732772767543793},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14774715900421143},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.1396925151348114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242789506912231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6607316136360168},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.6260080337524414},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5949521064758301},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.504491925239563},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.41880717873573303},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4148402810096741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3732772767543793},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14774715900421143},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.1396925151348114},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6287821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.676.854","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iis.sinica.edu.tw/papers/asriver/1772-F.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1576667197","https://openalex.org/W1979955134","https://openalex.org/W2109298029","https://openalex.org/W2113229563","https://openalex.org/W2116373735","https://openalex.org/W2116750654","https://openalex.org/W2162124943","https://openalex.org/W2169375076","https://openalex.org/W2296587773","https://openalex.org/W6634393904","https://openalex.org/W6676823600","https://openalex.org/W6683737379","https://openalex.org/W6697408455"],"related_works":["https://openalex.org/W2063547430","https://openalex.org/W2524993630","https://openalex.org/W2607244263","https://openalex.org/W2234430299","https://openalex.org/W1831690014","https://openalex.org/W1561022130","https://openalex.org/W1995263003","https://openalex.org/W2222580448","https://openalex.org/W4206700937","https://openalex.org/W1516392727"],"abstract_inverted_index":{"Visualizing":[0],"audio":[1,21],"signals":[2],"during":[3],"playback":[4],"has":[5],"long":[6],"been":[7],"a":[8,52,65,96,108,121],"fundamental":[9],"function":[10],"of":[11,67,110,125,145,156],"music":[12,40,48,54,83,92,127,141,159],"players.":[13],"However,":[14],"most":[15],"visual":[16],"effects":[17],"are":[18],"generated":[19],"by":[20],"signal":[22],"processing":[23],"directly":[24],"and":[25,107,154],"render":[26],"meaningless":[27],"or":[28],"incomprehensible":[29],"displays":[30],"to":[31,88,115],"users.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36,135],"present":[37],"an":[38,102],"intelligent":[39],"player":[41,58],"called":[42],"the":[43,56,75,79,82,91,117,126,131,148,152,157],"Playing":[44],"with":[45,74],"Tagging":[46],"(PWT)":[47],"player.":[49],"By":[50],"integrating":[51],"real-time":[53,132],"tagger,":[55],"PWT":[57],"can":[59],"display":[60],"dynamic":[61],"tag":[62,68,80,118,137],"distributions":[63],"via":[64],"set":[66],"bars":[69],"that":[70],"move":[71],"in":[72],"sync":[73],"music.":[76],"To":[77,129],"synchronize":[78],"distributions,":[81],"tagger":[84],"must":[85],"be":[86],"able":[87],"online":[89],"recognize":[90],"tags.":[93],"We":[94],"utilize":[95],"Gaussian":[97],"mixture":[98,109],"model":[99],"(GMM)":[100],"as":[101],"auditory":[103],"feature":[104],"encoding":[105],"reference":[106],"tag-based":[111],"aspect":[112],"models":[113],"(TBAMs)":[114],"predict":[116],"distribution":[119],"for":[120],"short":[122,140],"sliding":[123],"chunk":[124],"played.":[128],"evaluate":[130],"tagging":[133,160],"function,":[134],"simulate":[136],"prediction":[138],"on":[139,147],"chunks.":[142],"The":[143],"results":[144],"experiments":[146],"MajorMiner":[149],"dataset":[150],"demonstrate":[151],"potential":[153],"effectiveness":[155],"proposed":[158],"method.":[161]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
