{"id":"https://openalex.org/W4416799033","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249086","title":"Quality Assessment of DNN-Based Algorithms for Music Boundary Detection","display_name":"Quality Assessment of DNN-Based Algorithms for Music Boundary Detection","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799033","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249086"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5026747040","display_name":"Aneeka Azmat","orcid":null},"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":"Aneeka Azmat","raw_affiliation_strings":["Social Networks and HumanCentered Computing, Taiwan International Graduate Program, Institute of Information Science, Academia Sinica,Taiwan"],"affiliations":[{"raw_affiliation_string":"Social Networks and HumanCentered Computing, Taiwan International Graduate Program, Institute of Information Science, Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","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":["Social Networks and HumanCentered Computing, Taiwan International Graduate Program, Institute of Information Science, Academia Sinica,Taiwan"],"affiliations":[{"raw_affiliation_string":"Social Networks and HumanCentered Computing, Taiwan International Graduate Program, Institute of Information Science, Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034696208","display_name":"Cheng-Hsin Hsu","orcid":"https://orcid.org/0000-0002-8116-2591"},"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"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"ChengHsin Hsu","raw_affiliation_strings":["Institute of Information Systems and Applications, National Tsing Hua University,Hsinchu City,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Systems and Applications, National Tsing Hua University,Hsinchu City,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026747040"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4792946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"210","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9531000256538391,"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":0.9531000256538391,"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":0.023499999195337296,"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":0.011099999770522118,"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/spectrogram","display_name":"Spectrogram","score":0.6711000204086304},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6700999736785889},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6639000177383423},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.6255999803543091},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5429999828338623},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.5304999947547913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45239999890327454},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.45019999146461487},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4447999894618988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063999772071838},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6711000204086304},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6700999736785889},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6639000177383423},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.6255999803543091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5993000268936157},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.42750000953674316},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3662000000476837},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35690000653266907},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3287000060081482},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3264000117778778},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":9,"referenced_works":["https://openalex.org/W2478051194","https://openalex.org/W2936774411","https://openalex.org/W3098447809","https://openalex.org/W3198250510","https://openalex.org/W3215600992","https://openalex.org/W4224944643","https://openalex.org/W4288072961","https://openalex.org/W4312805589","https://openalex.org/W4386763510"],"related_works":[],"abstract_inverted_index":{"Music":[0],"boundary":[1],"detection":[2],"in":[3],"music":[4,118],"structure":[5],"analysis":[6],"has":[7],"traditionally":[8],"relied":[9],"on":[10],"objective":[11,33],"metrics":[12],"that":[13],"may":[14],"not":[15],"align":[16],"with":[17,53,144,180],"human":[18],"perception.":[19],"This":[20],"paper":[21],"introduces":[22],"a":[23,166,181],"user":[24,124],"study":[25],"driven":[26],"evaluation":[27,40,93,107,127],"pipeline":[28],"combining":[29],"three":[30],"stage":[31],"evaluation:":[32],"performance,":[34],"subjective":[35],"listener":[36,137,178],"ratings":[37],"and":[38,70,103,154,172],"meta":[39],"of":[41,148,159,183],"metric":[42,134],"validity.":[43],"Audio":[44],"is":[45,94,108],"first":[46],"converted":[47],"into":[48],"normalized":[49],"log-mel":[50],"spectrograms":[51],"augmented":[52],"SpecAugment.":[54],"Lightweight":[55],"deep":[56],"neural":[57,62,73],"network":[58,63,74],"(DNN)":[59],"algorithms:":[60],"convolutional":[61,71],"(CNN),":[64],"bidirectional":[65],"long":[66],"short-term":[67],"memory":[68],"(BiLSTM),":[69],"recurrent":[72],"(CRNN)":[75],"are":[76,86],"trained":[77],"to":[78,131],"produce":[79],"boundary-confidence":[80],"curves,":[81],"from":[82,116],"which":[83,133],"discrete":[84],"timestamps":[85],"extracted":[87],"by":[88,96,110],"empirically":[89],"tuned":[90],"thresholds.":[91],"Objective":[92],"measured":[95],"precision,":[97],"recall,":[98],"<tex":[99,149,155,160,167,184],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[100,150,156,161,168,185],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{F":[101,157],"1}$</tex>-score":[102,158],"Information":[104,173],"Gain.":[105],"Subjective":[106],"computed":[109],"mean":[111],"opinion":[112],"scores":[113],"(MOS)":[114],"collected":[115],"ten":[117],"experts":[119],"using":[120],"our":[121],"web-based":[122],"graphical":[123],"interface.":[125],"Meta":[126],"uses":[128],"Pearson":[129],"correlation":[130,182],"reveal":[132],"best":[135],"detects":[136],"judgments.":[138],"On":[139],"the":[140,176],"SALAMI":[141],"dataset,":[142],"CNN":[143],"SpecAugment":[145],"achieves":[146],"precision":[147],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{0.":[151,162,169,186],"5":[152],"0}$</tex>":[153],"4":[163],"2}$</tex>":[164],"at":[165],"5}$</tex>-second":[170],"tolerance,":[171],"Gain":[174],"shows":[175],"strongest":[177],"alignment":[179],"6":[187],"0}$</tex>.":[188]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}