{"id":"https://openalex.org/W7148543973","doi":"https://doi.org/10.1109/asru65441.2025.11434719","title":"Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation","display_name":"Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148543973","doi":"https://doi.org/10.1109/asru65441.2025.11434719"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132813149","display_name":"Hongming Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongming Guo","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073918837","display_name":"Ruibo Fu","orcid":"https://orcid.org/0000-0001-9598-1881"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Fu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102820117","display_name":"Yanli Geng","orcid":"https://orcid.org/0000-0002-4329-6476"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhong Geng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099083611","display_name":"Shuchen Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuchen Shi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453576","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0002-6785-1251"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028353824","display_name":"Chunyu Qiang","orcid":"https://orcid.org/0009-0007-2290-3074"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Qiang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132826944","display_name":"Ya Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132817663","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Tsinghua University,Beijing National Research Center for Information Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132817181","display_name":"Yukun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukun Liu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132793377","display_name":"Xuefei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefei Liu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007581833","display_name":"Chang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxing Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5132813149"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.754208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.24070000648498535,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.24070000648498535,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.18709999322891235,"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":0.07919999957084656,"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/component","display_name":"Component (thermodynamics)","score":0.7124000191688538},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5019999742507935},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.47360000014305115},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.3537999987602234},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3377000093460083},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.32839998602867126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333999872207642},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.7124000191688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5559999942779541},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5271999835968018},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3050999939441681},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2593116425","https://openalex.org/W2945761034","https://openalex.org/W4312933868","https://openalex.org/W4367359628","https://openalex.org/W4381786045","https://openalex.org/W4387969125","https://openalex.org/W4396877837","https://openalex.org/W4401043564","https://openalex.org/W4402111756","https://openalex.org/W4402715897","https://openalex.org/W4403674737","https://openalex.org/W7133212838"],"related_works":[],"abstract_inverted_index":{"Mainstream":[0],"Text-to-Audio":[1],"(TTA)":[2],"models":[3],"that":[4,45,76,105],"rely":[5],"on":[6,68],"Mel-spectrograms":[7],"often":[8],"struggle":[9],"to":[10,17,27],"generate":[11],"audio":[12],"with":[13,98],"rich":[14],"content,":[15],"leading":[16],"blurred":[18],"or":[19,92],"incoherent":[20],"outputs.":[21],"This":[22],"stems":[23],"from":[24],"an":[25],"inability":[26],"model":[28],"intricate":[29],"spectral":[30],"details":[31],"and":[32,43,50,94],"textures.":[33],"We":[34],"investigate":[35],"the":[36,51,64,108,111],"role":[37],"of":[38,110],"U-Net":[39],"components":[40,47,60],"in":[41,48],"generation":[42],"find":[44],"high-frequency":[46],"skip-connections":[49],"backbone":[52,59],"are":[53,61],"crucial":[54],"for":[55,63],"texture,":[56],"while":[57],"low-frequency":[58],"vital":[62],"denoising":[65],"process.":[66],"Based":[67],"this,":[69],"we":[70],"propose":[71],"\u201cMel-Refine,\u201d":[72],"a":[73],"plug-and-play":[74],"approach":[75],"enhances":[77],"Mel-spectrogram":[78],"quality":[79],"by":[80,116],"adjusting":[81],"component":[82],"weights":[83],"during":[84],"inference.":[85],"Our":[86],"method":[87],"requires":[88],"no":[89],"additional":[90],"training":[91],"fine-tuning":[93],"is":[95],"fully":[96],"compatible":[97],"any":[99],"diffusion-based":[100],"TTA":[101,113],"architecture.":[102],"Experiments":[103],"show":[104],"Mel-Refine":[106],"boosts":[107],"performance":[109],"latest":[112],"model,":[114],"Tango2,":[115],"$25":[117],"\\%$,":[118],"demonstrating":[119],"its":[120],"effectiveness.":[121]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}