{"id":"https://openalex.org/W2919634517","doi":"https://doi.org/10.1109/icassp.2019.8682765","title":"A Unified Neural Architecture for Instrumental Audio Tasks","display_name":"A Unified Neural Architecture for Instrumental Audio Tasks","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2919634517","doi":"https://doi.org/10.1109/icassp.2019.8682765","mag":"2919634517"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085092183","display_name":"Steven Spratley","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Steven Spratley","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Victoria, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026654079","display_name":"Daniel Beck","orcid":"https://orcid.org/0000-0001-9560-2773"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Daniel Beck","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Victoria, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078530959","display_name":"Trevor Cohn","orcid":"https://orcid.org/0000-0003-4363-1673"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Trevor Cohn","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Victoria, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":0.5735,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58535032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"26","issue":null,"first_page":"461","last_page":"465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9994000196456909,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.81814044713974},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7593103051185608},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5121397972106934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5043038129806519},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4930817782878876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48189598321914673},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4780700206756592},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4469677805900574},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41512900590896606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81814044713974},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7593103051185608},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5121397972106934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5043038129806519},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4930817782878876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48189598321914673},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4780700206756592},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4469677805900574},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41512900590896606},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1516853666","https://openalex.org/W1564265481","https://openalex.org/W1901129140","https://openalex.org/W2010362355","https://openalex.org/W2044011870","https://openalex.org/W2099471712","https://openalex.org/W2107328928","https://openalex.org/W2118774185","https://openalex.org/W2120847449","https://openalex.org/W2133665775","https://openalex.org/W2235761953","https://openalex.org/W2519091744","https://openalex.org/W2560254426","https://openalex.org/W2581073931","https://openalex.org/W2584505851","https://openalex.org/W2587994092","https://openalex.org/W2888839658","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2963952344","https://openalex.org/W2964135678","https://openalex.org/W2964243274","https://openalex.org/W4320013936","https://openalex.org/W6633711726","https://openalex.org/W6639824700","https://openalex.org/W6732251933","https://openalex.org/W6741681139","https://openalex.org/W6746700228","https://openalex.org/W6754608472"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W2898145319","https://openalex.org/W4289363934","https://openalex.org/W2098101267","https://openalex.org/W2059119686","https://openalex.org/W2898606530","https://openalex.org/W4289362680","https://openalex.org/W2403380333","https://openalex.org/W2761596192"],"abstract_inverted_index":{"Within":[0],"Music":[1],"Information":[2],"Retrieval":[3],"(MIR),":[4],"prominent":[5],"tasks":[6],"-":[7,14],"including":[8],"pitch-tracking,":[9],"source-separation,":[10],"super-resolution,":[11],"and":[12,97],"synthesis":[13],"typically":[15],"call":[16],"for":[17],"specialised":[18],"methods,":[19],"despite":[20],"their":[21],"similarities.":[22],"Conditional":[23],"Generative":[24],"Adversarial":[25],"Networks":[26],"(cGANs)":[27],"have":[28,41],"been":[29,44],"shown":[30],"to":[31,57,89,100,108,121],"be":[32],"highly":[33],"versatile":[34],"in":[35],"learning":[36],"general":[37,105],"image-to-image":[38],"translations,":[39],"but":[40],"not":[42],"yet":[43],"adapted":[45],"across":[46],"MIR.":[47],"In":[48,78],"this":[49],"work,":[50],"we":[51,81,114],"present":[52,115],"an":[53],"end-to-end":[54],"supervisable":[55],"architecture":[56],"perform":[58],"all":[59],"aforementioned":[60],"audio":[61],"tasks,":[62,92],"consisting":[63],"of":[64,72,85,103,111,119],"a":[65,73],"WaveNet":[66],"synthesiser":[67],"conditioned":[68],"on":[69],"the":[70,83,101,109,116],"output":[71],"jointly-trained":[74],"cGAN":[75],"spectrogram":[76],"translator.":[77],"doing":[79],"so,":[80],"demonstrate":[82],"potential":[84],"such":[86],"flexible":[87],"techniques":[88],"unify":[90],"MIR":[91],"promote":[93],"efficient":[94],"transfer":[95],"learning,":[96],"converge":[98],"research":[99],"improvement":[102],"powerful,":[104],"methods.":[106],"Finally,":[107],"best":[110],"our":[112],"knowledge,":[113],"first":[117],"application":[118],"GANs":[120],"guided":[122],"instrument":[123],"synthesis.":[124]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}