{"id":"https://openalex.org/W4392903243","doi":"https://doi.org/10.1109/icassp48485.2024.10446439","title":"BAE-Net: a Low Complexity and High Fidelity Bandwidth-Adaptive Neural Network for Speech Super-Resolution","display_name":"BAE-Net: a Low Complexity and High Fidelity Bandwidth-Adaptive Neural Network for Speech Super-Resolution","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903243","doi":"https://doi.org/10.1109/icassp48485.2024.10446439"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5025635655","display_name":"Guochen Yu","orcid":"https://orcid.org/0000-0002-7179-1044"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guochen Yu","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034844592","display_name":"Xiguang Zheng","orcid":"https://orcid.org/0000-0003-3103-9090"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiguang Zheng","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341075","display_name":"Nan Li","orcid":"https://orcid.org/0009-0003-9255-259X"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Li","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088910845","display_name":"Runqiang Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runqiang Han","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070266277","display_name":"Chengshi Zheng","orcid":"https://orcid.org/0000-0001-5656-994X"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengshi Zheng","raw_affiliation_strings":["Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Acoustics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374052","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0001-5773-9090"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022143957","display_name":"Chao Zhou","orcid":"https://orcid.org/0000-0002-7368-519X"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhou","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602683","display_name":"Qi Huang","orcid":"https://orcid.org/0000-0001-8911-5311"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Huang","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101544262","display_name":"Bing Yu","orcid":"https://orcid.org/0000-0002-1697-6089"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Yu","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5025635655"],"corresponding_institution_ids":["https://openalex.org/I4401726859"],"apc_list":null,"apc_paid":null,"fwci":2.2502,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87819895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"571","last_page":"575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.8213011026382446},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.7497789859771729},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6841869354248047},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.6718254089355469},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45648571848869324},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.44643038511276245},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4293265640735626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34669554233551025},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33190786838531494},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3305419087409973},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11432412266731262},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10254290699958801},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10210490226745605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213011026382446},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7497789859771729},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6841869354248047},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.6718254089355469},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45648571848869324},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.44643038511276245},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4293265640735626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34669554233551025},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33190786838531494},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3305419087409973},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11432412266731262},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10254290699958801},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10210490226745605},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":42,"referenced_works":["https://openalex.org/W1517841224","https://openalex.org/W1522137499","https://openalex.org/W1522301498","https://openalex.org/W2046820868","https://openalex.org/W2103934944","https://openalex.org/W2128767958","https://openalex.org/W2144404214","https://openalex.org/W2147152002","https://openalex.org/W2284050935","https://openalex.org/W2603567530","https://openalex.org/W2890648862","https://openalex.org/W2892335023","https://openalex.org/W2924508610","https://openalex.org/W2929274168","https://openalex.org/W2964121592","https://openalex.org/W2970006822","https://openalex.org/W2998161426","https://openalex.org/W2998572311","https://openalex.org/W3015338123","https://openalex.org/W3015837673","https://openalex.org/W3092028330","https://openalex.org/W3093990297","https://openalex.org/W3095802501","https://openalex.org/W3097945073","https://openalex.org/W3160652646","https://openalex.org/W3163243746","https://openalex.org/W3197260772","https://openalex.org/W3197334236","https://openalex.org/W3206809722","https://openalex.org/W4283215837","https://openalex.org/W4307323391","https://openalex.org/W4372260387","https://openalex.org/W4388620484","https://openalex.org/W6631190155","https://openalex.org/W6675521023","https://openalex.org/W6695676441","https://openalex.org/W6751200590","https://openalex.org/W6752483423","https://openalex.org/W6760993068","https://openalex.org/W6767111847","https://openalex.org/W6783867762","https://openalex.org/W6784457260"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2011561032","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/W2332512904"],"abstract_inverted_index":{"Speech":[0],"bandwidth":[1,34,57],"extension":[2,58],"(BWE)":[3],"has":[4],"demonstrated":[5],"promising":[6],"performance":[7,136],"in":[8,14,133],"enhancing":[9],"the":[10,29,32,67,78,83,90,101,129],"perceptual":[11],"speech":[12,69,91],"quality":[13],"real":[15],"communication":[16],"systems.":[17],"Most":[18],"existing":[19,143],"BWE":[20,145],"researches":[21],"primarily":[22],"focus":[23],"on":[24,110],"fixed":[25],"upsampling":[26],"ratios,":[27],"disregarding":[28],"fact":[30],"that":[31,99],"effective":[33,74],"of":[35,80,89,131,135],"captured":[36],"audio":[37],"may":[38],"fluctuate":[39],"frequently":[40],"due":[41],"to":[42,65],"various":[43],"capturing":[44],"devices":[45],"and":[46,72,86,104,123,137],"transmission":[47],"conditions.":[48],"In":[49],"this":[50,113],"paper,":[51],"we":[52,94],"propose":[53],"a":[54,96,120],"streaming":[55,122],"adaptive":[56],"solution":[59],"dubbed":[60],"BAE-Net,":[61],"which":[62,118],"is":[63,119],"suitable":[64],"handle":[66],"low-resolution":[68],"with":[70,142],"unknown":[71],"varying":[73],"bandwidth.":[75],"To":[76],"address":[77],"challenges":[79],"recovering":[81],"both":[82],"high-frequency":[84],"magnitude":[85,102],"phase":[87,105],"components":[88],"content":[92],"blindly,":[93],"devise":[95],"dual-stream":[97],"architecture":[98],"incorporates":[100],"inpainting":[103],"refinement.":[106],"For":[107],"potential":[108],"applications":[109],"edge":[111],"devices,":[112],"paper":[114],"also":[115],"introduces":[116],"BAE-NET-lite,":[117],"lightweight,":[121],"efficient":[124],"framework.":[125],"Quantitative":[126],"results":[127],"demonstrate":[128],"superiority":[130],"BAE-Net":[132],"terms":[134],"computational":[138],"efficiency":[139],"when":[140],"compared":[141],"state-of-the-art":[144],"methods.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
