{"id":"https://openalex.org/W4360996497","doi":"https://doi.org/10.1109/icct56141.2022.10073331","title":"Multi-scale Generative Adversarial Network for Speech Bandwidth Extension","display_name":"Multi-scale Generative Adversarial Network for Speech Bandwidth Extension","publication_year":2022,"publication_date":"2022-11-11","ids":{"openalex":"https://openalex.org/W4360996497","doi":"https://doi.org/10.1109/icct56141.2022.10073331"},"language":"en","primary_location":{"id":"doi:10.1109/icct56141.2022.10073331","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icct56141.2022.10073331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 22nd International Conference on Communication Technology (ICCT)","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/A5005839062","display_name":"Haosen Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haosen Lin","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology,Guangzhou,China","School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101795525","display_name":"Junmei Yang","orcid":"https://orcid.org/0000-0002-9677-0768"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junmei Yang","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology,Guangzhou,China","School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036647178","display_name":"Xikun Chen","orcid":"https://orcid.org/0000-0003-1077-2015"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xikun Chen","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology,Guangzhou,China","School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"1189","last_page":"1193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9983000159263611,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9830999970436096,"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":0.7791920900344849},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.7110342979431152},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6862298250198364},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5167137980461121},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5163237452507019},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4907878339290619},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.4737682640552521},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46601393818855286},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4584682583808899},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.447706937789917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41779565811157227},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.394228994846344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34865620732307434},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1252187192440033},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.11300346255302429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791920900344849},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.7110342979431152},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6862298250198364},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5167137980461121},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5163237452507019},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4907878339290619},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.4737682640552521},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46601393818855286},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4584682583808899},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.447706937789917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41779565811157227},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.394228994846344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34865620732307434},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1252187192440033},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.11300346255302429},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icct56141.2022.10073331","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icct56141.2022.10073331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 22nd International Conference on Communication Technology (ICCT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W99802290","https://openalex.org/W146900863","https://openalex.org/W1517841224","https://openalex.org/W1522137499","https://openalex.org/W1989337816","https://openalex.org/W2070450685","https://openalex.org/W2110311073","https://openalex.org/W2134017361","https://openalex.org/W2140188101","https://openalex.org/W2400830530","https://openalex.org/W2748163399","https://openalex.org/W2784918340","https://openalex.org/W2892335023","https://openalex.org/W2940120659","https://openalex.org/W2963470893","https://openalex.org/W2963952344","https://openalex.org/W3016022729","https://openalex.org/W3096159803","https://openalex.org/W3122318757","https://openalex.org/W3125868443","https://openalex.org/W3160652646","https://openalex.org/W3213952100","https://openalex.org/W4212774754","https://openalex.org/W4298289240","https://openalex.org/W6741681139","https://openalex.org/W6767111847","https://openalex.org/W6767367760"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W1604114751","https://openalex.org/W4252942110","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W2549308614","https://openalex.org/W3018584924","https://openalex.org/W4377694462","https://openalex.org/W1578591928"],"abstract_inverted_index":{"The":[0,63,103,156],"purpose":[1],"of":[2,24,29,53,100,115,121,135,145],"speech":[3,16,30,44,54],"bandwidth":[4,31,45],"extension":[5,32,46],"is":[6,66,85],"to":[7,58,109],"recover":[8],"the":[9,22,27,50,101,111,119,129,133,142],"high":[10],"frequency":[11,82,91,125],"information":[12],"missing":[13],"in":[14,78],"narrowband":[15],"signal.":[17],"In":[18,37,117],"recent":[19],"years,":[20],"with":[21,75,152],"introduction":[23],"neural":[25],"networks,":[26],"research":[28],"has":[33],"been":[34],"greatly":[35],"developed.":[36],"this":[38],"paper,":[39],"we":[40],"propose":[41],"a":[42,69,176],"new":[43],"method,":[47],"which":[48],"increases":[49],"sampling":[51],"rate":[52],"signal":[55],"from":[56],"8kHz":[57],"16kHz":[59],"and":[60,81,84,96,113,124,131,170,182],"48kHz":[61],"respectively.":[62],"model":[64],"architecture":[65],"based":[67],"on":[68,166],"multi-scale":[70,104],"generative":[71],"adversarial":[72,94],"network":[73],"(MSGan)":[74],"multiple":[76],"discriminators":[77,106],"both":[79],"time":[80,88,122],"domains,":[83],"trained":[86],"using":[87],"domain":[89,92,123,126],"loss,":[90,93],"loss":[95,99],"feature":[97],"matching":[98],"discriminators.":[102],"waveform":[105],"are":[107],"able":[108],"improve":[110],"naturalness":[112],"clarity":[114],"speech.":[116,147],"addition,":[118],"combination":[120],"can":[127],"stabilize":[128],"training":[130],"balance":[132,178],"weights":[134],"different":[136],"perceptual":[137,143],"quality":[138,144],"factors,":[139],"thereby":[140],"improving":[141],"wideband":[146],"We":[148],"compare":[149],"our":[150,160],"method":[151,161],"several":[153],"baseline":[154,164],"methods.":[155],"results":[157],"show":[158],"that":[159],"outperforms":[162],"other":[163],"methods":[165],"Log-Spectral":[167,172],"Distance":[168,173],"(LSD)":[169],"High-Frequency":[171],"(H-FLSD),":[174],"achieving":[175],"good":[177],"between":[179],"time-domain":[180],"metrics":[181],"frequency-domain":[183],"metrics.":[184]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}