{"id":"https://openalex.org/W4408355198","doi":"https://doi.org/10.1109/icassp49660.2025.10888627","title":"HiFi-SR: A Unified Generative Transformer-Convolutional Adversarial Network for High-Fidelity Speech Super-Resolution","display_name":"HiFi-SR: A Unified Generative Transformer-Convolutional Adversarial Network for High-Fidelity Speech Super-Resolution","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355198","doi":"https://doi.org/10.1109/icassp49660.2025.10888627"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5103758307","display_name":"Shengkui Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengkui Zhao","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101654458","display_name":"Kun Zhou","orcid":"https://orcid.org/0000-0002-7869-4474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zexu Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101758551","display_name":"Yukun Ma","orcid":"https://orcid.org/0000-0002-7055-3597"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukun Ma","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393899","display_name":"Chong Zhang","orcid":"https://orcid.org/0000-0002-2162-4344"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Zhang","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100595427","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-3724-4581"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9954000115394592,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9954000115394592,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9830999970436096,"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/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9315999746322632,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7499525547027588},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7211377620697021},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6261926889419556},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.5803973078727722},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5689606070518494},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5079367756843567},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4666241407394409},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4412165880203247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37340423464775085},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.23932957649230957},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13353046774864197},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1299881935119629},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11139139533042908},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09742370247840881},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09039255976676941},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07420185208320618}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7499525547027588},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7211377620697021},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6261926889419556},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.5803973078727722},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5689606070518494},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5079367756843567},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4666241407394409},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4412165880203247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37340423464775085},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.23932957649230957},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13353046774864197},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1299881935119629},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11139139533042908},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09742370247840881},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09039255976676941},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07420185208320618}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1591013319","https://openalex.org/W2134017361","https://openalex.org/W2135567392","https://openalex.org/W2400639714","https://openalex.org/W2400697507","https://openalex.org/W2407774997","https://openalex.org/W2593414223","https://openalex.org/W2802034954","https://openalex.org/W2972707556","https://openalex.org/W3095078764","https://openalex.org/W3125868443","https://openalex.org/W3197334236","https://openalex.org/W3197990672","https://openalex.org/W4221155904","https://openalex.org/W4283215837","https://openalex.org/W4307323391","https://openalex.org/W4375869348","https://openalex.org/W4385823130","https://openalex.org/W4392903177","https://openalex.org/W4392903251","https://openalex.org/W6741681139","https://openalex.org/W6749605826","https://openalex.org/W6757202746","https://openalex.org/W6757817989","https://openalex.org/W6767111847","https://openalex.org/W6783867762","https://openalex.org/W6802017037","https://openalex.org/W6838843145","https://openalex.org/W6853515095"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2888032422","https://openalex.org/W2945374968","https://openalex.org/W2996316059","https://openalex.org/W4293777179","https://openalex.org/W4385452045","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W2332512904"],"abstract_inverted_index":{"The":[0,87],"application":[1],"of":[2,78,138],"generative":[3],"adversarial":[4,57,131],"networks":[5,31],"(GANs)":[6],"has":[7],"recently":[8],"advanced":[9],"speech":[10,39,62,142,164],"super-resolution":[11],"(SR)":[12],"based":[13],"on":[14,26],"intermediate":[15],"representations":[16,36,80,108],"like":[17],"mel-spectrograms.":[18],"However,":[19],"existing":[20,163],"SR":[21,165],"methods":[22,166],"that":[23,54,159],"typically":[24],"rely":[25],"independently":[27],"trained":[28],"and":[29,37,81,147,171,178],"concatenated":[30],"may":[32],"lead":[33],"to":[34,59,72,150],"inconsistent":[35],"poor":[38],"quality,":[40],"especially":[41],"in":[42,129],"out-of-domain":[43,179],"scenarios.":[44,180],"In":[45],"this":[46],"work,":[47],"we":[48,116],"propose":[49],"HiFi-SR,":[50],"a":[51,67,92,118,125,151],"unified":[52,68],"network":[53,89,105],"leverages":[55],"end-to-end":[56],"training":[58,132],"achieve":[60],"high-fidelity":[61],"super-resolution.":[63],"Our":[64],"model":[65],"features":[66],"transformer-convolutional":[69],"generator":[70],"designed":[71],"seamlessly":[73],"handle":[74],"both":[75,168,176],"the":[76,103,130],"prediction":[77],"latent":[79,99],"their":[82],"conversion":[83],"into":[84,98,109],"time-domain":[85],"waveforms.":[86,111],"transformer":[88],"serves":[90],"as":[91],"powerful":[93],"encoder,":[94],"converting":[95],"low-resolution":[96],"mel-spectrograms":[97],"space":[100],"representations,":[101],"while":[102],"convolutional":[104],"upscales":[106],"these":[107],"high-resolution":[110],"To":[112],"enhance":[113],"high-frequency":[114],"fidelity,":[115],"incorporate":[117],"multi-band,":[119],"multi-scale":[120,126],"time-frequency":[121],"discriminator,":[122],"along":[123],"with":[124],"mel-reconstruction":[127],"loss":[128],"process.":[133],"HiFi-SR":[134,160],"is":[135],"versatile,":[136],"capable":[137],"upscaling":[139],"any":[140],"input":[141],"signal":[143],"between":[144],"4":[145],"kHz":[146,149,153],"32":[148],"48":[152],"sampling":[154],"rate.":[155],"Experimental":[156],"results":[157],"demonstrate":[158],"significantly":[161],"outperforms":[162],"across":[167],"objective":[169],"metrics":[170],"ABX":[172],"preference":[173],"tests,":[174],"for":[175],"in-domain":[177]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}