{"id":"https://openalex.org/W4372346850","doi":"https://doi.org/10.1109/icassp49357.2023.10095105","title":"DSPGAN: A Gan-Based Universal Vocoder for High-Fidelity TTS by Time-Frequency Domain Supervision from DSP","display_name":"DSPGAN: A Gan-Based Universal Vocoder for High-Fidelity TTS by Time-Frequency Domain Supervision from DSP","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346850","doi":"https://doi.org/10.1109/icassp49357.2023.10095105"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100722258","display_name":"Kun Song","orcid":"https://orcid.org/0000-0001-6110-2770"},"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/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/A5013928267","display_name":"Yi Lei","orcid":"https://orcid.org/0000-0002-9256-9311"},"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":"Yi Lei","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/A5016567570","display_name":"Hanzhao Li","orcid":"https://orcid.org/0009-0005-3215-7517"},"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":"Hanzhao Li","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/A5100713778","display_name":"Gang He","orcid":"https://orcid.org/0000-0002-9064-3418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang He","raw_affiliation_strings":["TAL Education Group,Beijing,China","TAL Education Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TAL Education Group,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036032938","display_name":"Jinfeng Bai","orcid":"https://orcid.org/0000-0001-8940-480X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinfeng Bai","raw_affiliation_strings":["TAL Education Group,Beijing,China","TAL Education Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TAL Education Group,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4474,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90959183,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9994000196456909,"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":0.9984999895095825,"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/spectrogram","display_name":"Spectrogram","score":0.9349705576896667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7342855334281921},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.6694850921630859},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6397545337677002},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5539667010307312},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5159116983413696},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.457767516374588},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.43726563453674316},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43689393997192383},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43520379066467285},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.42554205656051636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3822765648365021},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19077759981155396},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10974809527397156},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.08592760562896729},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08330661058425903}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9349705576896667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7342855334281921},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.6694850921630859},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6397545337677002},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5539667010307312},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5159116983413696},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.457767516374588},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.43726563453674316},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43689393997192383},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43520379066467285},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.42554205656051636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3822765648365021},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19077759981155396},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10974809527397156},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.08592760562896729},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08330661058425903},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2049686551","https://openalex.org/W2471520273","https://openalex.org/W2527729766","https://openalex.org/W2747070883","https://openalex.org/W2963091184","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W2993118648","https://openalex.org/W3000389243","https://openalex.org/W3015338123","https://openalex.org/W3092028330","https://openalex.org/W3096429957","https://openalex.org/W3129651364","https://openalex.org/W3144035034","https://openalex.org/W3169905056","https://openalex.org/W3198533616","https://openalex.org/W4221151538","https://openalex.org/W4226332109","https://openalex.org/W4287761884","https://openalex.org/W4296068811","https://openalex.org/W4395957972","https://openalex.org/W6727697161","https://openalex.org/W6755592152","https://openalex.org/W6767111847","https://openalex.org/W6771024825","https://openalex.org/W6771763809","https://openalex.org/W6779337556","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6803425590"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W4224231624","https://openalex.org/W1546240199","https://openalex.org/W2332512904"],"abstract_inverted_index":{"Recent":[0],"development":[1],"of":[2,17,156],"neural":[3,10,40],"vocoders":[4],"based":[5],"on":[6,22],"the":[7,74,85,90,94,98,102,107,111,120,124,130,135,144,149,157,166],"generative":[8],"adversarial":[9],"network":[11],"(GAN)":[12],"has":[13],"shown":[14],"obvious":[15],"advantages":[16],"generating":[18],"raw":[19],"waveform":[20,112],"conditioned":[21],"mel-spectrogram":[23,108,122],"with":[24,50],"fast":[25],"inference":[26,103],"speed":[27],"and":[28,54,97,152,169],"lightweight":[29],"networks.":[30],"Whereas,":[31],"it":[32,170],"is":[33],"still":[34],"challenging":[35],"to":[36,134,147],"train":[37],"a":[38,64,115],"universal":[39,66],"vocoder":[41,67],"that":[42,162],"can":[43,171],"synthesize":[44],"high-fidelity":[45,69,173],"speech":[46,70,174],"from":[47,78,110,123],"various":[48,154,176],"scenarios":[49],"unseen":[51],"speakers,":[52],"languages,":[53],"speaking":[55],"styles.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,105],"propose":[61],"DSP-":[62],"GAN,":[63],"GAN-based":[65,136,158],"for":[68,175],"synthesis":[71],"by":[72,89,114],"applying":[73],"time-frequency":[75,131],"domain":[76,132],"supervision":[77,133,146],"digital":[79],"signal":[80],"processing":[81],"(DSP).":[82],"To":[83],"eliminate":[84,153],"mismatch":[86],"problem":[87],"caused":[88],"ground-truth":[91],"spectrograms":[92,100],"in":[93,101],"training":[95],"phase":[96],"predicted":[99,121],"phase,":[104],"leverage":[106],"extracted":[109],"generated":[113],"DSP":[116],"module,":[117],"rather":[118],"than":[119],"Text-to-Speech":[125],"(TTS)":[126],"acoustic":[127],"model,":[128],"as":[129,143],"vocoder.":[137,159],"We":[138],"also":[139],"utilize":[140],"sine":[141],"excitation":[142],"time-domain":[145],"improve":[148],"harmonic":[150],"modeling":[151],"artifacts":[155],"Experiments":[160],"show":[161],"DSPGAN":[163],"significantly":[164],"outperforms":[165],"compared":[167],"approaches":[168],"generate":[172],"TTS":[177],"models":[178],"trained":[179],"using":[180],"diverse":[181],"data.":[182],"<sup":[183],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[184],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}