{"id":"https://openalex.org/W6949706634","doi":"https://doi.org/10.5281/zenodo.14877323","title":"Automatic Estimation of Singing Voice Musical Dynamics","display_name":"Automatic Estimation of Singing Voice Musical Dynamics","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6949706634","doi":"https://doi.org/10.5281/zenodo.14877323"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877323","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877323","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.14877323","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jyoti Narang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jyoti Narang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Nazif Can Tamer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nazif Can Tamer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Viviana De La Vega","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viviana De La Vega","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xavier Serra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Serra","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":0.43917399,"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":0.7921000123023987,"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":0.7921000123023987,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.047200001776218414,"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"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.04529999941587448,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9096999764442444},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.7423999905586243},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.5946000218391418},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5928000211715698},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.3450999855995178},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3206999897956848}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9096999764442444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7713000178337097},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.7423999905586243},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6212000250816345},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.5946000218391418},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4392000138759613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4269999861717224},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C2776275044","wikidata":"https://www.wikidata.org/wiki/Q192822","display_name":"Tonality","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877323","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877323","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.14877323","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877323","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":{"Musical":[0],"dynamics":[1,16,61,150,176],"form":[2],"a":[3,33,45,56,104,156],"core":[4],"part":[5],"of":[6,14,29,35,87,95,118,147,173],"expressive":[7,96],"singing":[8,18,63,174],"voice":[9,19,64,175],"performances.":[10],"However,":[11],"automatic":[12],"analysis":[13],"musical":[15,60,120,149],"for":[17,47,92,130,170,187],"has":[20],"received":[21],"limited":[22],"attention":[23,106],"partly":[24],"due":[25],"to":[26,114],"the":[27,51,83,99,116,131,171,182,191],"scarcity":[28],"suitable":[30],"datasets":[31],"and":[32,75,136],"lack":[34],"clear":[36],"evaluation":[37],"frameworks.":[38],"To":[39],"address":[40],"this":[41],"challenge,":[42],"we":[43,54,102,142],"propose":[44],"methodology":[46],"dataset":[48,57,146,179],"curation.":[49],"Employing":[50],"proposed":[52],"methodology,":[53],"compile":[55],"comprising":[58],"509":[59],"annotated":[62,151],"performances,":[65],"aligned":[66],"with":[67,110,155,181],"163":[68],"score":[69],"files,":[70],"leveraging":[71],"state-of-the-art":[72],"source":[73],"separation":[74],"alignment":[76],"techniques.":[77],"The":[78,178],"scores":[79],"are":[80],"sourced":[81],"from":[82],"OpenScore":[84],"Lieder":[85],"corpus":[86],"romantic-era":[88],"compositions,":[89],"widely":[90],"known":[91],"its":[93],"wealth":[94],"annotations.":[97],"Utilizing":[98],"curated":[100],"dataset,":[101],"train":[103],"multi-head":[105],"based":[107,138,166],"CNN":[108],"model":[109,132],"varying":[111],"window":[112],"sizes":[113],"evaluate":[115],"effectiveness":[117],"estimating":[119],"dynamics.":[121],"We":[122,159],"explored":[123],"two":[124],"distinct":[125],"perceptually":[126],"motivated":[127],"input":[128],"representations":[129],"training:":[133],"log-Mel":[134],"spectrum":[135],"bark-scale":[137,165],"features.":[139],"For":[140],"testing,":[141],"manually":[143],"curate":[144],"another":[145],"25":[148],"performances":[152],"in":[153],"collaboration":[154],"professional":[157],"vocalist.":[158],"conclude":[160],"through":[161],"our":[162],"experiments":[163],"that":[164],"features":[167],"outperform":[168],"log-Mel-features":[169],"task":[172],"prediction.":[177],"along":[180],"code":[183],"is":[184],"shared":[185],"publicly":[186],"further":[188],"research":[189],"on":[190],"topic.":[192]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}