{"id":"https://openalex.org/W6893219620","doi":"https://doi.org/10.5281/zenodo.14877371","title":"Mel-RoFormer for Vocal Separation and Vocal Melody Transcription","display_name":"Mel-RoFormer for Vocal Separation and Vocal Melody Transcription","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6893219620","doi":"https://doi.org/10.5281/zenodo.14877371"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877371","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877371","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.14877371","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ju-Chiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wei-Tsung Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Tsung Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jitong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jitong Chen","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.451200008392334,"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/T10860","display_name":"Speech and Audio Processing","score":0.451200008392334,"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/T11309","display_name":"Music and Audio Processing","score":0.35359999537467957,"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":0.10660000145435333,"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/singing","display_name":"Singing","score":0.6420000195503235},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6061999797821045},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5598999857902527},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.4489000141620636},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41499999165534973},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3783999979496002},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.3698999881744385},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3695000112056732},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.36660000681877136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955000162124634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6603999733924866},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6420000195503235},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3783999979496002},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C553614217","wikidata":"https://www.wikidata.org/wiki/Q685884","display_name":"Vocal music","level":4,"score":0.3495999872684479},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2888000011444092},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.27140000462532043},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.2603999972343445}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877371","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877371","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.14877371","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877371","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Developing":[0],"a":[1,43,50,132,137,143,151],"versatile":[2],"deep":[3],"neural":[4],"network":[5],"to":[6,19,58,63,75,90],"model":[7,45,77,153],"music":[8,26,193],"audio":[9,108,194],"is":[10,16],"crucial":[11],"in":[12,25,175,190],"MIR.":[13],"This":[14],"task":[15],"challenging":[17],"due":[18],"the":[20,56,60,78,184],"intricate":[21],"spectral":[22],"variations":[23],"inherent":[24],"signals,":[27,122],"which":[28,147],"convey":[29],"melody,":[30],"harmonics,":[31],"and":[32,71,80,98,110,179,186],"timbres":[33],"of":[34,130,188],"diverse":[35],"instruments.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,135,141,167],"introduce":[41],"Mel-RoFormer,":[42],"spectrogram-based":[44],"featuring":[46],"two":[47,84,92],"key":[48],"designs:":[49],"novel":[51],"Mel-band":[52],"Projection":[53],"module":[54],"at":[55,103],"front-end":[57],"enhance":[59],"model's":[61],"capability":[62],"capture":[64],"informative":[65],"features":[66],"across":[67],"multiple":[68],"frequency":[69,79],"bands,":[70],"interleaved":[72],"RoPE":[73],"Transformers":[74],"explicitly":[76],"time":[81],"dimensions":[82],"as":[83,150],"separate":[85],"sequences.":[86],"We":[87],"apply":[88],"Mel-RoFormer":[89,189],"tackle":[91],"essential":[93],"MIR":[94],"tasks:":[95],"vocal":[96,99,144,157,177],"separation":[97,145,178],"melody":[100,158,180],"transcription,":[101],"aimed":[102],"isolating":[104],"singing":[105,121],"voices":[106],"from":[107],"mixtures":[109],"transcribing":[111],"their":[112,117],"lead":[113],"melodies,":[114],"respectively.":[115],"Despite":[116],"shared":[118],"focus":[119],"on":[120,164],"these":[123],"tasks":[124],"possess":[125],"distinct":[126],"optimization":[127],"objectives.":[128],"Instead":[129],"training":[131],"unified":[133],"model,":[134,146],"adopt":[136],"two-step":[138],"approach.":[139],"Initially,":[140],"train":[142],"subsequently":[148],"serves":[149],"foundation":[152],"for":[154,156],"fine-tuning":[155],"transcription.":[159],"Through":[160],"extensive":[161],"experiments":[162],"conducted":[163],"benchmark":[165],"datasets,":[166],"showcase":[168],"that":[169],"our":[170],"models":[171],"achieve":[172],"state-of-the-art":[173],"performance":[174],"both":[176],"transcription":[181],"tasks,":[182],"underscoring":[183],"efficacy":[185],"versatility":[187],"modeling":[191],"complex":[192],"signals.":[195]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}