{"id":"https://openalex.org/W3160652646","doi":"https://doi.org/10.1109/icassp39728.2021.9413575","title":"Bandwidth Extension is All You Need","display_name":"Bandwidth Extension is All You Need","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160652646","doi":"https://doi.org/10.1109/icassp39728.2021.9413575","mag":"3160652646"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5101859099","display_name":"Jiaqi Su","orcid":"https://orcid.org/0000-0001-6038-0808"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Su","raw_affiliation_strings":["Princeton University,USA","Princeton University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University,USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714801","display_name":"Yunyun Wang","orcid":"https://orcid.org/0000-0003-1612-3681"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyun Wang","raw_affiliation_strings":["Princeton University,USA","Princeton University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University,USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034842939","display_name":"Adam Finkelstein","orcid":"https://orcid.org/0000-0001-9422-5363"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Finkelstein","raw_affiliation_strings":["Princeton University,USA","Princeton University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University,USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research,USA","Adobe Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Research, USA","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"696","last_page":"700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9991000294685364,"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":0.8100199699401855},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.7342081069946289},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.7148401737213135},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.6891227960586548},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6567395329475403},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5531439185142517},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5519869327545166},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5297637581825256},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5091220736503601},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.49407675862312317},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.45896458625793457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4529690444469452},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44990476965904236},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32405513525009155},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.256198525428772},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.17014679312705994},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10100361704826355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8100199699401855},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.7342081069946289},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.7148401737213135},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.6891227960586548},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6567395329475403},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5531439185142517},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5519869327545166},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5297637581825256},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5091220736503601},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.49407675862312317},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.45896458625793457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4529690444469452},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44990476965904236},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32405513525009155},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.256198525428772},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.17014679312705994},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10100361704826355},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":58,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1517841224","https://openalex.org/W1522137499","https://openalex.org/W1994997782","https://openalex.org/W2086381917","https://openalex.org/W2151667147","https://openalex.org/W2221409856","https://openalex.org/W2284050935","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2739619458","https://openalex.org/W2757519008","https://openalex.org/W2784918340","https://openalex.org/W2801903454","https://openalex.org/W2802034954","https://openalex.org/W2805669069","https://openalex.org/W2890648862","https://openalex.org/W2890983311","https://openalex.org/W2892335023","https://openalex.org/W2940120659","https://openalex.org/W2940290905","https://openalex.org/W2944438111","https://openalex.org/W2951310434","https://openalex.org/W2952218014","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963685250","https://openalex.org/W2963782041","https://openalex.org/W2963952344","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2970006822","https://openalex.org/W2972707556","https://openalex.org/W2975414524","https://openalex.org/W2996286887","https://openalex.org/W2998639482","https://openalex.org/W3002439978","https://openalex.org/W3015805741","https://openalex.org/W3016022729","https://openalex.org/W3016166140","https://openalex.org/W3017350693","https://openalex.org/W3096159803","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3104557543","https://openalex.org/W3122318757","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W6603838645","https://openalex.org/W6681996158","https://openalex.org/W6695676441","https://openalex.org/W6727697161","https://openalex.org/W6741681139","https://openalex.org/W6748409065","https://openalex.org/W6751928472","https://openalex.org/W6767111847","https://openalex.org/W6772622344","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W4375869276","https://openalex.org/W4221152531","https://openalex.org/W2046186789","https://openalex.org/W2653453860","https://openalex.org/W1998521395","https://openalex.org/W2118159520","https://openalex.org/W2032652622","https://openalex.org/W4224931722","https://openalex.org/W3215881519","https://openalex.org/W3160652646"],"abstract_inverted_index":{"Speech":[0],"generation":[1,128],"and":[2,29,43,129,132,157],"enhancement":[3],"have":[4],"seen":[5],"recent":[6,126],"breakthroughs":[7],"in":[8,90,137],"quality":[9,91,139],"thanks":[10],"to":[11,26,65,106,121,150,163,167],"deep":[12,80],"learning.":[13],"These":[14],"methods":[15,42,166],"typically":[16,111],"operate":[17],"at":[18],"a":[19,35,54,72,78,147],"limited":[20],"sampling":[21,169],"rate":[22],"of":[23,40,45,125],"16-22kHz":[24],"due":[25],"computational":[27],"complexity":[28],"available":[30],"datasets.":[31],"This":[32,51],"limitation":[33],"imposes":[34],"gap":[36,153],"between":[37,154],"the":[38,123,152,161],"output":[39,124],"such":[41,165],"that":[44,60,100,109],"high-fidelity":[46,115],"(\u226544kHz)":[47],"real-world":[48],"audio":[49],"applications.":[50],"paper":[52],"proposes":[53],"new":[55],"bandwidth":[56],"extension":[57],"(BWE)":[58],"method":[59,68,120],"expands":[61],"8-16kHz":[62],"speech":[63,127,156],"signals":[64],"48kHz.":[66],"The":[67],"is":[69,104,110],"based":[70],"on":[71],"feed-forward":[73],"WaveNet":[74],"architecture":[75],"trained":[76],"with":[77],"GAN-based":[79],"feature":[81],"loss.":[82],"A":[83],"mean-opinion-score":[84],"(MOS)":[85],"experiment":[86],"shows":[87],"significant":[88,135],"improvement":[89,136],"over":[92,140],"state-of-the-art":[93],"BWE":[94,103],"methods.":[95],"An":[96],"AB":[97],"test":[98],"reveals":[99],"our":[101,119],"16-to-48kHz":[102],"able":[105],"achieve":[107],"fidelity":[108],"indistinguishable":[112],"from":[113],"real":[114],"recordings.":[116],"We":[117,143],"use":[118],"enhance":[122],"denoising":[130],"methods,":[131],"experiments":[133],"demonstrate":[134],"sound":[138],"these":[141],"baselines.":[142],"propose":[144],"this":[145],"as":[146],"general":[148],"approach":[149],"narrow":[151],"generated":[155],"recorded":[158],"speech,":[159],"without":[160],"need":[162],"adapt":[164],"higher":[168],"rates.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}