{"id":"https://openalex.org/W3161691227","doi":"https://doi.org/10.1109/icassp39728.2021.9415061","title":"A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music","display_name":"A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161691227","doi":"https://doi.org/10.1109/icassp39728.2021.9415061","mag":"3161691227"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5046330926","display_name":"Hanbin Bae","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hanbin Bae","raw_affiliation_strings":["Speech AI Lab, NCSOFT Corp., Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab, NCSOFT Corp., Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060429696","display_name":"Jae\u2010sung Bae","orcid":"https://orcid.org/0000-0002-8270-0072"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Sung Bae","raw_affiliation_strings":["Speech AI Lab, NCSOFT Corp., Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab, NCSOFT Corp., Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101800027","display_name":"Young-Sun Joo","orcid":"https://orcid.org/0000-0002-7428-5868"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Sun Joo","raw_affiliation_strings":["Speech AI Lab, NCSOFT Corp., Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab, NCSOFT Corp., Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059648356","display_name":"Young-Ik Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Ik Kim","raw_affiliation_strings":["Speech AI Lab, NCSOFT Corp., Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab, NCSOFT Corp., Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052468556","display_name":"Hoon Young Cho","orcid":"https://orcid.org/0000-0002-6850-6580"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoon-Young Cho","raw_affiliation_strings":["Speech AI Lab, NCSOFT Corp., Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab, NCSOFT Corp., Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046330926"],"corresponding_institution_ids":["https://openalex.org/I4210135449"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61402404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"80","issue":null,"first_page":"6603","last_page":"6607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.8002959489822388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7263937592506409},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.585098385810852},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5494312047958374},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5330900549888611},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5063532590866089},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48786258697509766},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4286610186100006},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4223247766494751},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3684287965297699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3509714603424072},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07718595862388611}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8002959489822388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7263937592506409},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.585098385810852},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5494312047958374},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5330900549888611},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5063532590866089},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48786258697509766},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4286610186100006},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4223247766494751},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3684287965297699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3509714603424072},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07718595862388611},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W2071128523","https://openalex.org/W2120847449","https://openalex.org/W2514828952","https://openalex.org/W2587994092","https://openalex.org/W2767052532","https://openalex.org/W2794490148","https://openalex.org/W2903739847","https://openalex.org/W2907262790","https://openalex.org/W2963452667","https://openalex.org/W2963534259","https://openalex.org/W2963691546","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2972466499","https://openalex.org/W2973062255","https://openalex.org/W3091427154","https://openalex.org/W4298857617","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6745569068","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6751512325"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W642007152","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W1909292483","https://openalex.org/W2052688117","https://openalex.org/W596245619"],"abstract_inverted_index":{"Recently,":[0],"it":[1],"has":[2],"become":[3],"easier":[4],"to":[5,22,57],"obtain":[6],"speech":[7,35,76,96,121,142],"data":[8],"from":[9,74],"various":[10],"media":[11],"such":[12],"as":[13],"the":[14,39,46,54,69,75,83,94,106,110,114,120,127,135],"internet":[15],"or":[16,124],"YouTube,":[17],"but":[18],"directly":[19],"utilizing":[20],"them":[21],"train":[23,59],"a":[24,79,98],"neural":[25],"text-to-speech":[26],"(TTS)":[27],"model":[28,63,85],"is":[29,36,72,91],"difficult.":[30],"The":[31,130],"proportion":[32],"of":[33,101,113,126],"clean":[34,102],"insufficient":[37],"and":[38,97],"remainder":[40],"includes":[41],"background":[42,70],"music.":[43],"Even":[44],"with":[45,64,86,93],"global":[47],"style":[48],"token":[49],"(GST).":[50],"Therefore,":[51],"we":[52],"propose":[53],"following":[55],"method":[56,137],"successfully":[58],"an":[60,87],"end-to-end":[61],"TTS":[62],"limited":[65],"broadcast":[66],"data.":[67],"First,":[68],"music":[71,80],"removed":[73],"by":[77],"introducing":[78],"filter.":[81],"Second,":[82],"GST-TTS":[84],"auxiliary":[88],"quality":[89,107,122],"classifier":[90,108],"trained":[92],"filtered":[95],"small":[99],"amount":[100],"speech.":[103,129],"In":[104],"particular,":[105],"makes":[109],"embedding":[111],"vector":[112],"GST":[115],"layer":[116],"focus":[117],"on":[118],"representing":[119],"(filtered":[123],"clean)":[125],"input":[128],"experimental":[131],"results":[132],"verified":[133],"that":[134],"proposed":[136],"synthesized":[138],"much":[139],"more":[140],"high-quality":[141],"than":[143],"conventional":[144],"methods.":[145]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}