{"id":"https://openalex.org/W6911320952","doi":"https://doi.org/10.5281/zenodo.10265373","title":"Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction","display_name":"Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6911320952","doi":"https://doi.org/10.5281/zenodo.10265373"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265373","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265373","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":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10265373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Keren Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Keren Shao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ke Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Taylor Berg-Kirkpatrick","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Shlomo Dubnov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shlomo Dubnov","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.30231832,"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":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9434999823570251,"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":0.9434999823570251,"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":0.017999999225139618,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.01510000042617321,"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":0.8755999803543091},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6021999716758728},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5688999891281128},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5418999791145325},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47920000553131104},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.476500004529953},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43639999628067017},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.4318000078201294},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.43070000410079956}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8755999803543091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6621999740600586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6618000268936157},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47920000553131104},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4433000087738037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.43070000410079956},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.3944999873638153},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3465000092983246},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C124062153","wikidata":"https://www.wikidata.org/wiki/Q7806645","display_name":"Time\u2013frequency representation","level":4,"score":0.32409998774528503},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C8590192","wikidata":"https://www.wikidata.org/wiki/Q1054694","display_name":"Frequency response","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.26750001311302185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265373","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265373","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":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.10265373","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265373","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":""},"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":{"In":[0,17],"deep":[1],"learning":[2],"research,":[3],"many":[4],"melody":[5,87,138],"extraction":[6],"models":[7],"rely":[8],"on":[9,32,54],"redesigning":[10],"neural":[11],"network":[12],"architectures":[13],"to":[14,107],"improve":[15],"performance.":[16],"this":[18],"paper,":[19],"we":[20,58,89],"propose":[21],"an":[22],"input":[23],"feature":[24],"modification":[25,30],"and":[26,63,73,113],"a":[27,84,91,114,121],"training":[28],"objective":[29],"based":[31],"two":[33],"assumptions.":[34],"First,":[35],"harmonics":[36],"in":[37],"the":[38,46,51,55,60,71,97,130],"spectrograms":[39],"of":[40],"audio":[41],"data":[42],"decay":[43],"rapidly":[44],"along":[45],"frequency":[47],"axis.":[48],"To":[49,82],"enhance":[50],"model's":[52],"sensitivity":[53],"trailing":[56],"harmonics,":[57],"modify":[59],"Combined":[61],"Frequency":[62],"Periodicity":[64],"(CFP)":[65],"representation":[66],"using":[67],"discrete":[68],"z-transform.":[69],"Second,":[70],"vocal":[72],"non-vocal":[74],"segments":[75],"with":[76],"extremely":[77],"short":[78],"duration":[79],"are":[80,133],"uncommon.":[81],"ensure":[83],"more":[85],"stable":[86],"contour,":[88],"design":[90],"differentiable":[92],"loss":[93],"function":[94],"that":[95,129],"prevents":[96],"model":[98],"from":[99,120],"predicting":[100],"such":[101],"segments.":[102],"We":[103],"apply":[104],"these":[105],"modifications":[106,132],"several":[108],"models,":[109],"including":[110],"MSNet,":[111],"FTANet,":[112],"newly":[115],"introduced":[116],"model,":[117],"PianoNet,":[118],"modified":[119],"piano":[122],"transcription":[123],"network.":[124],"Our":[125],"experimental":[126],"results":[127],"demonstrate":[128],"proposed":[131],"empirically":[134],"effective":[135],"for":[136],"singing":[137],"extraction.":[139]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}