{"id":"https://openalex.org/W2940405045","doi":"https://doi.org/10.1109/icassp.2019.8683154","title":"Singing Voice Synthesis Based on Generative Adversarial Networks","display_name":"Singing Voice Synthesis Based on Generative Adversarial Networks","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2940405045","doi":"https://doi.org/10.1109/icassp.2019.8683154","mag":"2940405045"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683154","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/A5086910479","display_name":"Yukiya Hono","orcid":"https://orcid.org/0000-0003-1245-8791"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukiya Hono","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594810","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0003-2081-0396"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049909008","display_name":"Keiichiro Oura","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6955","last_page":"6959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9912999868392944,"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/naturalness","display_name":"Naturalness","score":0.9291991591453552},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8505507707595825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7548394203186035},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7267616987228394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7120285034179688},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5623377561569214},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5341885089874268},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5043097734451294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4479031562805176},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12229415774345398},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0724588930606842}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9291991591453552},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8505507707595825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7548394203186035},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7267616987228394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7120285034179688},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5623377561569214},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5341885089874268},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5043097734451294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4479031562805176},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12229415774345398},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0724588930606842},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683154","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W102093577","https://openalex.org/W2049686551","https://openalex.org/W2099471712","https://openalex.org/W2102003408","https://openalex.org/W2112796928","https://openalex.org/W2125389028","https://openalex.org/W2134973740","https://openalex.org/W2154920538","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2166823384","https://openalex.org/W2173520492","https://openalex.org/W2402539796","https://openalex.org/W2405756170","https://openalex.org/W2515336442","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2746068898","https://openalex.org/W2890983311","https://openalex.org/W2949382160","https://openalex.org/W2963341071","https://openalex.org/W2963684088","https://openalex.org/W2963929654","https://openalex.org/W2963971656","https://openalex.org/W4320013936","https://openalex.org/W6604170644","https://openalex.org/W6675380101","https://openalex.org/W6678815747","https://openalex.org/W6684191040","https://openalex.org/W6685352114","https://openalex.org/W6713645886","https://openalex.org/W6732429163","https://openalex.org/W6743002019"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,92],"generative":[4,39],"adversarial":[5,40],"training":[6],"method":[7,107,111],"for":[8],"deep":[9],"neural":[10],"network":[11],"(DNN)-based":[12],"singing":[13,25,35,94,118],"voice":[14,26,36,95],"synthesis.":[15,86],"The":[16],"DNN-based":[17,93],"approach":[18],"has":[19],"been":[20],"used":[21],"in":[22,48,63,84,112],"statistical":[23],"parametric":[24],"synthesis":[27,56,96],"and":[28,70],"improved":[29],"the":[30,33,65,73,80,99,105,109,113,116],"naturalness":[31,114],"of":[32,67,115],"synthesized":[34,117],"[1].":[37],"Recently,":[38],"networks":[41],"(GANs)":[42],"[2]":[43],"have":[44,59,72],"attracted":[45],"significant":[46],"attention":[47],"various":[49],"machine":[50],"learning":[51],"research":[52],"areas":[53],"including":[54],"speech":[55,82,85],"[3].":[57],"GANs":[58],"achieved":[60],"great":[61],"success":[62],"modeling":[64],"distributions":[66],"complex":[68],"data,":[69],"they":[71],"potential":[74],"to":[75],"alleviate":[76],"over-smoothing":[77],"problem":[78],"on":[79],"generated":[81],"parameters":[83],"In":[87],"this":[88],"paper,":[89],"we":[90],"propose":[91],"system":[97],"incorporating":[98],"GAN.":[100],"Experimental":[101],"results":[102],"show":[103],"that":[104],"proposed":[106],"outperforms":[108],"conventional":[110],"voice.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}