{"id":"https://openalex.org/W7108644313","doi":"https://doi.org/10.5281/zenodo.17811473","title":"Simple and Effective Semantic Song Segmentation","display_name":"Simple and Effective Semantic Song Segmentation","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108644313","doi":"https://doi.org/10.5281/zenodo.17811473"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811473","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811473","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811473","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Filip Korzeniowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Filip Korzeniowski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Richard Vogl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard Vogl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.53764004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9704999923706055,"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":0.9704999923706055,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.0027000000700354576,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.002199999988079071,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.6980999708175659},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6747999787330627},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5934000015258789},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5656999945640564},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.483599990606308},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46869999170303345},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44350001215934753},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4223000109195709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893999814987183},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6980999708175659},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6747999787330627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6611999869346619},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5934000015258789},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5656999945640564},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40529999136924744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38019999861717224},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2969000041484833},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2653999924659729},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811473","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811473","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811473","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811473","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,93],"propose":[1,83],"a":[2,14,35],"simple,":[3],"yet":[4],"effective":[5],"approach":[6],"to":[7,19,66],"semantic":[8],"song":[9,111],"segmentation.":[10],"Our":[11],"model":[12],"is":[13],"convolutional":[15],"neural":[16],"network":[17],"trained":[18],"jointly":[20],"predict":[21],"frame-wise":[22],"boundary":[23],"activation":[24],"functions":[25],"and":[26,39,61,70,101,108,113],"segment":[27],"label":[28],"probabilities.":[29],"The":[30],"input":[31],"features":[32],"consist":[33],"of":[34,110,120,127],"log-magnitude":[36],"log-frequency":[37],"spectrogram":[38],"self-similarity":[40],"lag":[41],"matrices,":[42],"combining":[43],"modern":[44],"deep":[45],"learning":[46],"approaches":[47],"with":[48],"hand-crafted":[49],"features.":[50],"To":[51],"evaluate":[52],"our":[53,128],"approach,":[54],"we":[55,82,123],"first":[56],"examine":[57],"commonly":[58],"used":[59],"datasets":[60,103],"find":[62],"substantial":[63],"overlap":[64,78],"(up":[65],"22%)":[67],"between":[68,98],"training":[69],"testing":[71],"sets":[72],"(SALAMI":[73],"vs.":[74],"RWC-Pop).":[75],"As":[76],"this":[77],"invalidates":[79],"meaningful":[80],"comparisons,":[81],"using":[84],"the":[85,117,125],"previously":[86],"unexplored":[87],"McGill":[88,99],"Billboard":[89,100],"dataset":[90],"for":[91],"testing.":[92],"carefully":[94],"eliminate":[95],"duplicate":[96],"entries":[97],"other":[102],"through":[104],"both":[105],"audio":[106],"fingerprinting":[107],"string-matching":[109],"titles":[112],"artist":[114],"names.":[115],"Using":[116],"resulting":[118],"set":[119],"719":[121],"tracks,":[122],"demonstrate":[124],"effectiveness":[126],"approach.":[129]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-05T00:00:00"}