{"id":"https://openalex.org/W4408353361","doi":"https://doi.org/10.1109/icassp49660.2025.10889911","title":"Progressive Subband Modeling for Artifacts-free Speech Super-resolution","display_name":"Progressive Subband Modeling for Artifacts-free Speech Super-resolution","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353361","doi":"https://doi.org/10.1109/icassp49660.2025.10889911"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889911","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889911","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":"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/A5100770748","display_name":"Donghyun Kim","orcid":"https://orcid.org/0000-0002-2063-5551"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Donghyun Kim","raw_affiliation_strings":["Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002418613","display_name":"Joon\u2010Hyuk Chang","orcid":"https://orcid.org/0000-0003-2610-2323"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100770748"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05404759,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9905999898910522,"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":0.9905999898910522,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9413999915122986,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9340000152587891,"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/computer-science","display_name":"Computer science","score":0.7104774713516235},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5705921053886414},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.45611804723739624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3483959138393402}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7104774713516235},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5705921053886414},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.45611804723739624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3483959138393402}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889911","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889911","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":39,"referenced_works":["https://openalex.org/W1517841224","https://openalex.org/W1552314771","https://openalex.org/W1591013319","https://openalex.org/W1980741455","https://openalex.org/W2004018702","https://openalex.org/W2100285470","https://openalex.org/W2141998673","https://openalex.org/W2167341025","https://openalex.org/W2171815504","https://openalex.org/W2172065531","https://openalex.org/W2296073425","https://openalex.org/W2400697507","https://openalex.org/W2516001803","https://openalex.org/W2560647685","https://openalex.org/W2802253983","https://openalex.org/W2888169323","https://openalex.org/W3021546974","https://openalex.org/W3045520545","https://openalex.org/W3094893721","https://openalex.org/W3097538987","https://openalex.org/W3123742938","https://openalex.org/W3142849873","https://openalex.org/W3144035034","https://openalex.org/W3163243746","https://openalex.org/W3211264909","https://openalex.org/W3213952100","https://openalex.org/W4283215837","https://openalex.org/W4293363567","https://openalex.org/W4372260387","https://openalex.org/W4382202681","https://openalex.org/W4391149056","https://openalex.org/W4392904360","https://openalex.org/W4395447416","https://openalex.org/W4401609277","https://openalex.org/W4402118937","https://openalex.org/W6741681139","https://openalex.org/W6767367760","https://openalex.org/W6772349387","https://openalex.org/W6847544085"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,56],"consider":[4,29],"new":[5],"reconstruction":[6],"loss":[7,18],"together":[8],"with":[9,107],"a":[10],"subband":[11,49],"objective":[12],"in":[13,86],"the":[14,38,70,74,78,93,113],"form":[15],"of":[16,32,96],"auxiliary":[17],"function":[19],"for":[20,35,62],"artifacts-free":[21],"speech":[22,36,106],"super-resolution.":[23],"Unlike":[24],"prior":[25],"work":[26],"which":[27],"mainly":[28],"full":[30],"band":[31],"frequency":[33],"region":[34],"super-resolution,":[37],"proposed":[39,71,102],"method":[40,72,103],"alleviates":[41],"distortion":[42],"generated":[43],"during":[44],"deep":[45],"learning":[46,61],"training":[47],"via":[48],"modeling.":[50],"To":[51],"further":[52],"minimize":[53],"spectral":[54],"artifacts,":[55],"also":[57],"apply":[58],"progressive":[59],"curriculum":[60],"superior":[63],"performance.":[64],"Our":[65],"experimental":[66],"results":[67],"demonstrate":[68],"that":[69,100],"outperforms":[73],"evaluated":[75],"baselines":[76],"on":[77],"both":[79,87],"TIMIT":[80],"and":[81,89,112],"VCTK":[82],"dataset":[83],"by":[84],"increase":[85],"intelligibility":[88],"perceptual":[90],"score.":[91],"Furthermore,":[92],"visual":[94],"representation":[95],"spectrograms":[97],"comparison":[98],"verify":[99],"our":[101],"clearly":[104],"restoring":[105],"fewer":[108],"artifacts.":[109],"Audio":[110],"samples":[111],"implementations":[114],"are":[115],"available":[116],"online.<sup":[117],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[118],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[119]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}