{"id":"https://openalex.org/W4319585868","doi":"https://doi.org/10.1109/iscslp57327.2022.10038120","title":"Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS","display_name":"Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319585868","doi":"https://doi.org/10.1109/iscslp57327.2022.10038120"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038120","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100722267","display_name":"Kun Song","orcid":"https://orcid.org/0000-0002-6379-2805"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Song","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064364353","display_name":"Jian Cong","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cong","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115547209","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0002-7528-4621"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060467975","display_name":"Yongmao Zhang","orcid":"https://orcid.org/0009-0000-0526-5778"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongmao Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101443742","display_name":"Ning Jiang","orcid":"https://orcid.org/0000-0002-7152-3621"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Jiang","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100379077","display_name":"Haiying Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiying Wu","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3114,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.54476544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"75"},"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/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":0.9994999766349792,"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":0.7257974147796631},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6919732093811035},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.626600444316864},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5503175854682922},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5237155556678772},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.496704638004303},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4783874750137329},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44403311610221863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34016597270965576},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12916728854179382}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257974147796631},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6919732093811035},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.626600444316864},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5503175854682922},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5237155556678772},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.496704638004303},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4783874750137329},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44403311610221863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34016597270965576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12916728854179382},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10038120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038120","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2049686551","https://openalex.org/W2095705004","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2560674852","https://openalex.org/W2747070883","https://openalex.org/W2747329762","https://openalex.org/W2884225676","https://openalex.org/W2913668833","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W3015338123","https://openalex.org/W3144035034","https://openalex.org/W3197273793","https://openalex.org/W4226332109","https://openalex.org/W4395957972","https://openalex.org/W6674330103","https://openalex.org/W6748409065","https://openalex.org/W6767111847","https://openalex.org/W6771024825","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6800720828","https://openalex.org/W6803425590"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W4380714744","https://openalex.org/W2387995142","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2964074194","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"In":[0],"current":[1],"two-stage":[2],"neural":[3,14],"text-to-speech":[4],"(TTS)":[5],"paradigm,":[6],"it":[7],"is":[8,19],"ideal":[9],"to":[10,21,59,82,106],"have":[11],"a":[12,54,63,130],"universal":[13,131],"vocoder,":[15,132],"once":[16],"trained,":[17],"which":[18,68,86],"robust":[20],"imperfect":[22],"mel-spectrogram":[23],"predicted":[24],"from":[25],"the":[26,39,60,83,111],"acoustic":[27],"model.":[28],"To":[29,95],"this":[30],"end,":[31],"we":[32,52,77,100],"propose":[33],"Robust":[34,124],"MelGAN":[35,125],"vocoder":[36],"by":[37],"solving":[38],"original":[40],"multi-band":[41],"MelGAN\u2019s":[42],"metallic":[43,88],"sound":[44,135],"problem":[45],"and":[46,74,90,118],"increasing":[47],"its":[48],"generalization":[49,98],"ability.":[50],"Specifically,":[51],"introduce":[53,101],"fine-grained":[55],"network":[56,80],"dropout":[57,81],"strategy":[58],"generator.":[61],"With":[62],"specifically":[64],"designed":[65],"over-smooth":[66],"handler":[67],"separates":[69],"speech":[70],"signal":[71],"intro":[72],"periodic":[73],"aperiodic":[75],"components,":[76,85],"only":[78],"perform":[79],"aperodic":[84],"alleviates":[87],"sounding":[89],"maintains":[91],"good":[92],"speaker":[93],"similarity.":[94],"further":[96],"improve":[97],"ability,":[99],"several":[102],"data":[103,109],"augmentation":[104],"methods":[105],"augment":[107],"fake":[108],"in":[110,137],"discriminator,":[112],"including":[113],"harmonic":[114,116],"shift,":[115],"noise":[117],"phase":[119],"noise.":[120],"Experiments":[121],"show":[122],"that":[123],"can":[126],"be":[127],"used":[128],"as":[129],"significantly":[133],"improving":[134],"quality":[136],"TTS":[138],"systems":[139],"built":[140],"on":[141],"various":[142],"types":[143],"of":[144],"data.":[145],"<sup":[146,149],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[147,150],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[148,151],"Audio":[152],"samples":[153],"are":[154],"available":[155],"at":[156],"https://RobustMelGAN.github.io/RobustMelGAN/":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}