{"id":"https://openalex.org/W4413155119","doi":"https://doi.org/10.1109/lsp.2025.3598729","title":"Is GAN Necessary for Mel-Spectrogram-Based Neural Vocoder?","display_name":"Is GAN Necessary for Mel-Spectrogram-Based Neural Vocoder?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413155119","doi":"https://doi.org/10.1109/lsp.2025.3598729"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3598729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3598729","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5067982618","display_name":"Hui-Peng Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui-Peng Du","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-9831-6086","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6668-022X","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066498315","display_name":"Rui-Chen Zheng","orcid":"https://orcid.org/0009-0000-8074-9553"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui-Chen Zheng","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-8074-9553","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072371384","display_name":"Ye-Xin Lu","orcid":"https://orcid.org/0009-0009-8026-0702"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye-Xin Lu","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0009-8026-0702","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10027255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"3485","last_page":"3489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8773000240325928,"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/T10320","display_name":"Neural Networks and Applications","score":0.8773000240325928,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9149273633956909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6576745510101318},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5623417496681213},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46907633543014526},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3521369695663452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3476863503456116}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9149273633956909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6576745510101318},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5623417496681213},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46907633543014526},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3521369695663452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3476863503456116}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3598729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3598729","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2545034164","display_name":null,"funder_award_id":"2308085QF200","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G5861301885","display_name":null,"funder_award_id":"62301521","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2749609415","https://openalex.org/W2749651610","https://openalex.org/W2803595463","https://openalex.org/W2951310434","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W3015338123","https://openalex.org/W3163845842","https://openalex.org/W4221152438","https://openalex.org/W4225956675","https://openalex.org/W4372260247","https://openalex.org/W4377000449","https://openalex.org/W4385807442","https://openalex.org/W4386076493","https://openalex.org/W4391806982","https://openalex.org/W4392903177","https://openalex.org/W4392904136","https://openalex.org/W4402111624","https://openalex.org/W4402112619","https://openalex.org/W4403510204","https://openalex.org/W4405521053","https://openalex.org/W4406461725"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W2942893872","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Recently,":[0],"mainstream":[1],"mel-spectrogram-based":[2,49],"neural":[3,50,117],"vocoders":[4,118],"rely":[5],"on":[6],"generative":[7],"adversarial":[8],"network":[9],"(GAN)":[10],"for":[11,48,63,81],"high-fidelity":[12],"speech":[13,96],"generation,":[14],"e.g.,":[15],"HiFi-GAN":[16],"and":[17,27,74,113],"BigVGAN.":[18],"However,":[19],"the":[20,41,61,82,87,95],"use":[21],"of":[22,43,89,98,104],"GAN":[23,45,64],"restricts":[24],"training":[25,111],"efficiency":[26,112],"model":[28],"complexity.":[29,114],"Therefore,":[30],"this":[31],"letter":[32],"proposes":[33],"a":[34],"novel":[35],"FreeGAN":[36,53,99],"vocoder,":[37],"aiming":[38],"to":[39,79,102],"answer":[40],"question":[42],"whether":[44],"is":[46,100],"necessary":[47],"vocoders.":[51],"The":[52],"employs":[54],"an":[55],"amplitude-phase":[56],"serial":[57],"prediction":[58],"framework,":[59],"eliminating":[60],"need":[62],"training.":[65],"It":[66],"incorporates":[67],"amplitude":[68],"prior":[69],"input,":[70],"SNAKE-ConvNeXt":[71],"v2":[72],"backbone":[73],"frequency-weighted":[75],"anti-wrapping":[76],"phase":[77],"loss":[78,84],"compensate":[80],"performance":[83],"caused":[85],"by":[86],"absence":[88],"GAN.":[90],"Experimental":[91],"results":[92],"confirm":[93],"that":[94,103],"quality":[97],"comparable":[101],"advanced":[105],"GAN-based":[106],"vocoders,":[107],"while":[108],"significantly":[109],"improving":[110],"Other":[115],"explicit-phase-prediction-based":[116],"can":[119],"also":[120],"work":[121],"without":[122],"GAN,":[123],"leveraging":[124],"our":[125],"proposed":[126],"methods.":[127]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}