{"id":"https://openalex.org/W4372341094","doi":"https://doi.org/10.1109/icassp49357.2023.10097255","title":"HIFI++: A Unified Framework for Bandwidth Extension and Speech Enhancement","display_name":"HIFI++: A Unified Framework for Bandwidth Extension and Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341094","doi":"https://doi.org/10.1109/icassp49357.2023.10097255"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5008290260","display_name":"Pavel Andreev","orcid":"https://orcid.org/0000-0001-9645-4418"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]},{"id":"https://openalex.org/I4210141363","display_name":"Samsung (Russia)","ror":"https://ror.org/051an6p98","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210141363"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Pavel Andreev","raw_affiliation_strings":["Samsung AI Center,Moscow","Skolkovo Institute of Science and Technology, Moscow","Higher School of Economics, Moscow","Samsung AI Center, Moscow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center,Moscow","institution_ids":["https://openalex.org/I4210141363"]},{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow","institution_ids":["https://openalex.org/I125989756"]},{"raw_affiliation_string":"Higher School of Economics, Moscow","institution_ids":["https://openalex.org/I118501908"]},{"raw_affiliation_string":"Samsung AI Center, Moscow","institution_ids":["https://openalex.org/I4210141363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051275168","display_name":"Aibek Alanov","orcid":null},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I4210141363","display_name":"Samsung (Russia)","ror":"https://ror.org/051an6p98","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210141363"]},{"id":"https://openalex.org/I4392021246","display_name":"AIRI - Artificial Intelligence Research Institute","ror":"https://ror.org/014a87f14","country_code":"RU","type":"nonprofit","lineage":["https://openalex.org/I4392021246"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Aibek Alanov","raw_affiliation_strings":["Samsung AI Center,Moscow","Samsung AI Center, Moscow","Artificial Intelligence Research Institute, Moscow","Higher School of Economics, Moscow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center,Moscow","institution_ids":["https://openalex.org/I4210141363"]},{"raw_affiliation_string":"Samsung AI Center, Moscow","institution_ids":["https://openalex.org/I4210141363"]},{"raw_affiliation_string":"Artificial Intelligence Research Institute, Moscow","institution_ids":["https://openalex.org/I4392021246"]},{"raw_affiliation_string":"Higher School of Economics, Moscow","institution_ids":["https://openalex.org/I118501908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007660603","display_name":"Oleg V. Ivanov","orcid":"https://orcid.org/0000-0003-4443-7514"},"institutions":[{"id":"https://openalex.org/I4210141363","display_name":"Samsung (Russia)","ror":"https://ror.org/051an6p98","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210141363"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Oleg Ivanov","raw_affiliation_strings":["Samsung AI Center,Moscow","Samsung AI Center, Moscow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center,Moscow","institution_ids":["https://openalex.org/I4210141363"]},{"raw_affiliation_string":"Samsung AI Center, Moscow","institution_ids":["https://openalex.org/I4210141363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101595563","display_name":"Dmitry Vetrov","orcid":"https://orcid.org/0000-0001-6863-9028"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I4392021246","display_name":"AIRI - Artificial Intelligence Research Institute","ror":"https://ror.org/014a87f14","country_code":"RU","type":"nonprofit","lineage":["https://openalex.org/I4392021246"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry Vetrov","raw_affiliation_strings":["Higher School of Economics,Moscow","Higher School of Economics, Moscow","Artificial Intelligence Research Institute, Moscow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Higher School of Economics,Moscow","institution_ids":["https://openalex.org/I118501908"]},{"raw_affiliation_string":"Higher School of Economics, Moscow","institution_ids":["https://openalex.org/I118501908"]},{"raw_affiliation_string":"Artificial Intelligence Research Institute, Moscow","institution_ids":["https://openalex.org/I4392021246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4667,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.97616689,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.8042011857032776},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.7258929014205933},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.6977595686912537},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6389446258544922},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4800892472267151},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.47759342193603516},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4580177366733551},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44314831495285034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3478736877441406},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.13310575485229492},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.11015263199806213},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09788122773170471},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09143853187561035},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08649569749832153},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.07845550775527954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042011857032776},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.7258929014205933},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.6977595686912537},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6389446258544922},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4800892472267151},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47759342193603516},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4580177366733551},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44314831495285034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3478736877441406},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.13310575485229492},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.11015263199806213},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09788122773170471},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09143853187561035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08649569749832153},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.07845550775527954},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":26,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2141998673","https://openalex.org/W2593414223","https://openalex.org/W2757519008","https://openalex.org/W2963189033","https://openalex.org/W2963452667","https://openalex.org/W2964058413","https://openalex.org/W2970006822","https://openalex.org/W2972745527","https://openalex.org/W2998572311","https://openalex.org/W3092028330","https://openalex.org/W3095095816","https://openalex.org/W3097945073","https://openalex.org/W3125868443","https://openalex.org/W3163243746","https://openalex.org/W3197624376","https://openalex.org/W3197912330","https://openalex.org/W3206809722","https://openalex.org/W4224133928","https://openalex.org/W4225302959","https://openalex.org/W6751512325","https://openalex.org/W6767111847","https://openalex.org/W6767367760","https://openalex.org/W6772349387","https://openalex.org/W6783867762","https://openalex.org/W6792466957"],"related_works":["https://openalex.org/W2075768550","https://openalex.org/W3022218857","https://openalex.org/W2171218219","https://openalex.org/W2380075625","https://openalex.org/W2369178846","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W2059847929","https://openalex.org/W3005996785","https://openalex.org/W4386984417"],"abstract_inverted_index":{"Generative":[0],"adversarial":[1],"networks":[2],"have":[3],"recently":[4],"demonstrated":[5],"outstanding":[6],"performance":[7],"in":[8,70],"neural":[9],"vocoding":[10],"outperforming":[11],"best":[12],"autoregressive":[13],"and":[14,51],"flow-based":[15],"models.":[16],"In":[17,35],"this":[18,23],"paper,":[19],"we":[20,41],"show":[21,55],"that":[22,56],"success":[24],"can":[25],"be":[26],"extended":[27],"to":[28],"other":[29],"tasks":[30,72],"of":[31,81,89],"conditional":[32],"audio":[33],"generation.":[34],"particular,":[36],"building":[37],"upon":[38],"HiFi":[39],"vocoders,":[40],"propose":[42],"a":[43,87],"novel":[44],"HiFi++":[45,62],"general":[46],"frame-work":[47],"for":[48],"bandwidth":[49],"extension":[50],"speech":[52],"enhancement.":[53],"We":[54],"with":[57,67],"the":[58,68],"improved":[59],"generator":[60],"architecture,":[61],"performs":[63],"better":[64],"or":[65],"comparably":[66],"state-of-the-art":[69],"these":[71],"while":[73],"spending":[74],"significantly":[75],"less":[76],"computational":[77],"resources.":[78],"The":[79],"effectiveness":[80],"our":[82],"approach":[83],"is":[84],"validated":[85],"through":[86],"series":[88],"extensive":[90],"experiments.":[91]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-05-07T00:00:00"}
