{"id":"https://openalex.org/W3097508615","doi":"https://doi.org/10.21437/interspeech.2020-1984","title":"Speech-to-Singing Conversion Based on Boundary Equilibrium GAN","display_name":"Speech-to-Singing Conversion Based on Boundary Equilibrium GAN","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097508615","doi":"https://doi.org/10.21437/interspeech.2020-1984","mag":"3097508615"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1984","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1984","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":["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/A5017182348","display_name":"Da-Yi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Da-Yi Wu","raw_affiliation_strings":["Department of CSIE, National Taiwan University","Research Center for IT Innovation, Academia Sincia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSIE, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sincia","institution_ids":["https://openalex.org/I4210086894"]}]},{"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/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Research Center for IT Innovation, Academia Sincia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sincia","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061291906"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1316","last_page":"1320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8006367683410645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5973076224327087},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5560125708580017},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.500417947769165},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3640952408313751},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.18449455499649048},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.127680242061615},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.06465345621109009}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8006367683410645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5973076224327087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5560125708580017},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.500417947769165},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3640952408313751},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.18449455499649048},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.127680242061615},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.06465345621109009}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1984","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1984","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W2067709094","https://openalex.org/W2108382268","https://openalex.org/W2120847449","https://openalex.org/W2150933458","https://openalex.org/W2191779130","https://openalex.org/W2407685581","https://openalex.org/W2502312327","https://openalex.org/W2519091744","https://openalex.org/W2849790107","https://openalex.org/W2905741299","https://openalex.org/W2916985722","https://openalex.org/W2937242376","https://openalex.org/W2945478979","https://openalex.org/W2948211236","https://openalex.org/W2962866891","https://openalex.org/W2963233633","https://openalex.org/W2964070952","https://openalex.org/W2964243274","https://openalex.org/W2964607787","https://openalex.org/W2970006822","https://openalex.org/W2973046048","https://openalex.org/W2996286887","https://openalex.org/W3005991431","https://openalex.org/W3010943931","https://openalex.org/W3015645837","https://openalex.org/W3024973272","https://openalex.org/W3046715528","https://openalex.org/W3114301328","https://openalex.org/W3133525064","https://openalex.org/W4287802874","https://openalex.org/W4294643831","https://openalex.org/W4295274059","https://openalex.org/W4320013936","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,23,27,45,49,53,57,68,105],"use":[4],"of":[5,48,59],"generative":[6],"adversarial":[7],"network":[8],"(GAN)-based":[9],"models":[10],"for":[11],"converting":[12],"a":[13,17,36,41,60,64,71,95],"speech":[14,42],"signal":[15,62],"into":[16,92],"singing":[18,51,61,109],"one,":[19],"without":[20],"reference":[21],"to":[22],"phoneme":[24],"sequence":[25],"underlying":[26],"speech.This":[28],"is":[29,89],"achieved":[30],"by":[31],"viewing":[32],"speech-to-singing":[33],"conversion":[34],"as":[35],"style":[37],"transfer":[38],"problem.Specifically,":[39],"given":[40],"input,":[43],"and":[44,85,100],"F0":[46],"contour":[47],"target":[50],"output,":[52],"proposed":[54,106],"model":[55,69,107],"generates":[56,108],"spectrogram":[58,88],"with":[63,94,111],"progressive-growing":[65],"encoder/decoder":[66],"architecture.Moreover,":[67],"uses":[70],"boundary":[72],"equilibrium":[73],"GAN":[74],"loss":[75],"term":[76],"such":[77],"that":[78,104],"it":[79],"can":[80],"learn":[81],"from":[82],"both":[83],"paired":[84],"unpaired":[86],"data.The":[87],"finally":[90],"converted":[91],"wave":[93],"separate":[96],"GAN-based":[97],"vocoder.Our":[98],"quantitative":[99],"qualitative":[101],"analysis":[102],"show":[103],"voices":[110],"much":[112],"higher":[113],"naturalness":[114],"than":[115],"an":[116],"existing":[117],"non":[118],"adversarially-trained":[119],"baseline.":[120]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}