{"id":"https://openalex.org/W4416252290","doi":"https://doi.org/10.1109/waspaa66052.2025.11230926","title":"UBGAN: Enhancing Coded Speech with Blind and Guided Bandwidth Extension","display_name":"UBGAN: Enhancing Coded Speech with Blind and Guided Bandwidth Extension","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416252290","doi":"https://doi.org/10.1109/waspaa66052.2025.11230926"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.16404","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048846474","display_name":"Kishan Gupta","orcid":"https://orcid.org/0000-0002-4354-0758"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kishan Gupta","raw_affiliation_strings":["Fraunhofer IIS,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077147264","display_name":"Srikanth Korse","orcid":"https://orcid.org/0009-0008-7564-9628"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Srikanth Korse","raw_affiliation_strings":["International Audio Laboratories,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories,Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078105594","display_name":"Andreas Brendel","orcid":"https://orcid.org/0000-0002-6051-6346"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Brendel","raw_affiliation_strings":["Fraunhofer IIS,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039716073","display_name":"Nicola Pia","orcid":"https://orcid.org/0000-0003-0987-863X"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nicola Pia","raw_affiliation_strings":["Fraunhofer IIS,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054985419","display_name":"Guillaume Fuchs","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Guillaume Fuchs","raw_affiliation_strings":["Fraunhofer IIS,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39778491,"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":0.9194999933242798,"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":0.9194999933242798,"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":0.035999998450279236,"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"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.018300000578165054,"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/bandwidth-extension","display_name":"Bandwidth extension","score":0.8125},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7121000289916992},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5335000157356262},{"id":"https://openalex.org/keywords/wideband-audio","display_name":"Wideband audio","score":0.5052000284194946},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.48669999837875366},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4749999940395355},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.46810001134872437},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3864000141620636},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.37380000948905945}],"concepts":[{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.8125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946000099182129},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7121000289916992},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6089000105857849},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.5052000284194946},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4749999940395355},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.46810001134872437},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.32420000433921814},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3147999942302704},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C57667952","wikidata":"https://www.wikidata.org/wiki/Q1154443","display_name":"Variable bitrate","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.2680000066757202},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.16404","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.16404","pdf_url":"https://arxiv.org/pdf/2505.16404","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:publica.fraunhofer.de:publica/504840","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/504840","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.16404","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.16404","pdf_url":"https://arxiv.org/pdf/2505.16404","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416252290.pdf","grobid_xml":"https://content.openalex.org/works/W4416252290.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W1519690927","https://openalex.org/W2165291881","https://openalex.org/W2593414223","https://openalex.org/W2775336875","https://openalex.org/W2972519044","https://openalex.org/W2998733532","https://openalex.org/W3015368254","https://openalex.org/W3025844872","https://openalex.org/W3115185819","https://openalex.org/W3160652646","https://openalex.org/W3188073270","https://openalex.org/W3197042120","https://openalex.org/W3215615641","https://openalex.org/W4221155904","https://openalex.org/W4225287045","https://openalex.org/W4225860133","https://openalex.org/W4284972581","https://openalex.org/W4372260387","https://openalex.org/W4372270198","https://openalex.org/W4385823460","https://openalex.org/W4387870028","https://openalex.org/W4388117621","https://openalex.org/W4388118256","https://openalex.org/W4392903243","https://openalex.org/W4392903389","https://openalex.org/W4399875170","https://openalex.org/W4402112548","https://openalex.org/W4404035591","https://openalex.org/W4405521053","https://openalex.org/W4408353007"],"related_works":[],"abstract_inverted_index":{"In":[0,77,98],"practical":[1],"application":[2],"of":[3,8,14,57,63,90,134,138,154,197,212,223],"speech":[4,39,45,66,75,80],"codecs,":[5],"a":[6,87,107,123,135,185,189],"multitude":[7],"factors":[9],"such":[10,204],"as":[11,184],"the":[12,15,54,64,113,131,147,152,177,195,198,210,220],"quality":[13,56],"radio":[16],"connection,":[17],"limiting":[18],"hardware":[19],"or":[20],"required":[21],"user":[22],"experience":[23],"necessitate":[24],"trade-offs":[25],"between":[26],"achievable":[27],"perceptual":[28,55],"quality,":[29],"engendered":[30],"bitrate":[31,192,196],"and":[32,37,70,92,125,140,150,174,218,230],"computational":[33],"complexity.":[34],"Most":[35],"conventional":[36,74,139],"neural":[38,79,141],"codecs":[40,81,217,229],"operate":[41,105],"on":[42],"wideband":[43],"(WB)":[44],"signals":[46,156],"to":[47,86,104,160,194,215],"achieve":[48],"this":[49],"compromise.":[50],"To":[51],"further":[52,169],"enhance":[53],"coded":[58],"speech,":[59],"bandwidth":[60,153],"extension":[61],"(BWE)":[62],"transmitted":[65],"is":[67],"an":[68],"attractive":[69],"popular":[71],"technique":[72],"in":[73,146,164],"coding.":[76],"contrast,":[78],"are":[82,93,101],"typically":[83,102],"trained":[84,103],"end-to-end":[85],"specific":[88],"set":[89],"requirements":[91],"often":[94],"not":[95],"easily":[96],"adaptable.":[97],"particular,":[99],"they":[100],"at":[106,188],"single":[108],"fixed":[109],"sampling":[110],"rate.":[111],"With":[112],"Universal":[114],"Bandwidth":[115],"Extension":[116],"Generative":[117],"Adversarial":[118],"Network":[119],"(UBGAN),":[120],"we":[121],"propose":[122],"modular":[124],"lightweight":[126],"GAN-based":[127],"solution":[128],"that":[129],"increases":[130],"operational":[132],"flexibility":[133],"wide":[136],"range":[137],"codecs.":[142],"Our":[143,206],"model":[144],"operates":[145,202],"subband":[148],"domain":[149],"extends":[151],"WB":[155,216],"from":[157],"8":[158],"kHz":[159],"16":[161],"kHz,":[162],"resulting":[163],"super-wideband":[165],"(SWB)":[166],"signals.":[167],"We":[168],"introduce":[170],"two":[171],"variants,":[172],"guided-UBGAN":[173],"blind-UBGAN,":[175],"where":[176],"guided":[178],"version":[179],"transmits":[180],"quantized":[181],"learned":[182],"representation":[183],"side":[186],"information":[187],"very":[190],"low":[191],"additional":[193],"codec,":[199],"while":[200],"blind-BWE":[201],"without":[203],"side-information.":[205],"subjective":[207],"assessments":[208],"demonstrate":[209],"advantage":[211],"UBGAN":[213],"applied":[214],"highlight":[219],"generalization":[221],"capacity":[222],"our":[224],"proposed":[225],"method":[226],"across":[227],"multiple":[228],"bitrates.":[231]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-11-14T00:00:00"}