{"id":"https://openalex.org/W3024973272","doi":"https://doi.org/10.21437/interspeech.2020-1137","title":"Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization","display_name":"Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3024973272","doi":"https://doi.org/10.21437/interspeech.2020-1137","mag":"3024973272"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.08526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101719938","display_name":"Jen-Yu Liu","orcid":"https://orcid.org/0000-0003-1299-6688"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jen-Yu Liu","raw_affiliation_strings":["Taiwan AI Labs, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiwan AI Labs, Taipei, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012567144","display_name":"Yuhua Chen","orcid":"https://orcid.org/0000-0002-6350-6426"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Hua Chen","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017146803","display_name":"Yin-Cheng Yeh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin-Cheng Yeh","raw_affiliation_strings":["Taiwan AI Labs, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiwan AI Labs, Taipei, Taiwan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1997","last_page":"2001"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9986000061035156,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7773693799972534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7773029804229736},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6088656783103943},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6048031449317932},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.594458818435669},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4708399772644043},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.43375658988952637},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.4309905171394348},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4187874495983124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3155905306339264},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09260457754135132},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.08100089430809021}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7773693799972534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773029804229736},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6088656783103943},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6048031449317932},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.594458818435669},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4708399772644043},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.43375658988952637},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.4309905171394348},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4187874495983124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3155905306339264},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09260457754135132},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.08100089430809021},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.08526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.08526","pdf_url":"https://arxiv.org/pdf/2005.08526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.08526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.08526","pdf_url":"https://arxiv.org/pdf/2005.08526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1924770834","https://openalex.org/W2099471712","https://openalex.org/W2120605154","https://openalex.org/W2125389028","https://openalex.org/W2267126114","https://openalex.org/W2423557781","https://openalex.org/W2605195953","https://openalex.org/W2754229890","https://openalex.org/W2777302760","https://openalex.org/W2811079561","https://openalex.org/W2898148140","https://openalex.org/W2899724567","https://openalex.org/W2910577860","https://openalex.org/W2919624000","https://openalex.org/W2932319787","https://openalex.org/W2940544976","https://openalex.org/W2948211236","https://openalex.org/W2950547518","https://openalex.org/W2953318193","https://openalex.org/W2962706768","https://openalex.org/W2962793481","https://openalex.org/W2962942158","https://openalex.org/W2962981281","https://openalex.org/W2963306805","https://openalex.org/W2963373786","https://openalex.org/W2963804063","https://openalex.org/W2964199361","https://openalex.org/W2964243274","https://openalex.org/W2964607787","https://openalex.org/W2970006822","https://openalex.org/W2972706021","https://openalex.org/W2972867623","https://openalex.org/W2973046048","https://openalex.org/W2995005087","https://openalex.org/W2995233853","https://openalex.org/W3000389243","https://openalex.org/W3003673875","https://openalex.org/W3005991431","https://openalex.org/W3015843452","https://openalex.org/W3020570669","https://openalex.org/W3034794073","https://openalex.org/W3035574324","https://openalex.org/W3046715528","https://openalex.org/W3114301328","https://openalex.org/W3125709657","https://openalex.org/W4288107125","https://openalex.org/W4295274059","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"In":[0],"a":[1,7,32,80,97],"recent":[2],"paper,":[3],"we":[4,78,95,109],"have":[5],"presented":[6],"generative":[8],"adversarial":[9],"network":[10],"(GAN)-based":[11],"model":[12,27,116,134,147],"for":[13,62,119,125,169],"unconditional":[14],"generation":[15],"of":[16,19,25,35,44,56,113,152],"the":[17,23,26,54,57,74,84,91,102,111,114,136,146,159,167],"mel-spectrograms":[18,43],"singing":[20,121],"voices.":[21,128],"As":[22],"generator":[24,85,103],"is":[28],"designed":[29],"to":[30,86,101,104,148],"take":[31],"variable-length":[33],"sequence":[34],"noise":[36],"vectors":[37],"as":[38,164,166],"input,":[39],"it":[40],"can":[41],"generate":[42,150],"variable":[45],"length.":[46],"However,":[47],"our":[48,171],"previous":[49,71],"listening":[50],"test":[51],"shows":[52,131],"that":[53,70,132],"quality":[55],"generated":[58],"audio":[59],"leaves":[60],"room":[61],"improvement.":[63],"The":[64],"present":[65],"paper":[66,179],"extends":[67],"and":[68,141,154,157],"expands":[69],"work":[72],"in":[73,83,90],"following":[75],"aspects.":[76],"First,":[77],"employ":[79,145],"hierarchical":[81],"architecture":[82],"induce":[87],"some":[88],"structure":[89],"temporal":[92],"dimension.":[93],"Second,":[94],"introduce":[96],"cycle":[98],"regularization":[99],"mechanism":[100],"avoid":[105],"mode":[106],"collapse.":[107],"Third,":[108],"evaluate":[110],"performance":[112],"new":[115,133],"not":[117],"only":[118],"generating":[120,126],"voices,":[122],"but":[123],"also":[124,144],"speech":[127],"Evaluation":[129],"result":[130,160],"outperforms":[135],"prior":[137],"one":[138],"both":[139],"objectively":[140],"subjectively.":[142],"We":[143],"unconditionally":[149],"sequences":[151],"piano":[153],"violin":[155],"music":[156],"find":[158],"promising.":[161],"Audio":[162],"examples,":[163],"well":[165],"code":[168],"implementing":[170],"model,":[172],"will":[173],"be":[174],"publicly":[175],"available":[176],"online":[177],"upon":[178],"publication.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-05-21T00:00:00"}