{"id":"https://openalex.org/W4416250985","doi":"https://doi.org/10.1109/waspaa66052.2025.11230955","title":"A lightweight and robust method for blind wideband-to-fullband extension of speech","display_name":"A lightweight and robust method for blind wideband-to-fullband extension of speech","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250985","doi":"https://doi.org/10.1109/waspaa66052.2025.11230955"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230955","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":"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/A5042244085","display_name":"Jan B\u00fcthe","orcid":"https://orcid.org/0000-0001-5872-4325"},"institutions":[{"id":"https://openalex.org/I4210124678","display_name":"Xi'an University of Science and Education Foundation","ror":"https://ror.org/02ymk8b69","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210124678"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jan B\u00fcthe","raw_affiliation_strings":["Xiph&#x002E;org Foundation"],"affiliations":[{"raw_affiliation_string":"Xiph&#x002E;org Foundation","institution_ids":["https://openalex.org/I4210124678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[{"id":"https://openalex.org/I4210124678","display_name":"Xi'an University of Science and Education Foundation","ror":"https://ror.org/02ymk8b69","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210124678"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":["Xiph&#x002E;org Foundation"],"affiliations":[{"raw_affiliation_string":"Xiph&#x002E;org Foundation","institution_ids":["https://openalex.org/I4210124678"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042244085"],"corresponding_institution_ids":["https://openalex.org/I4210124678"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37379289,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.808899998664856,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.808899998664856,"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":0.13519999384880066,"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":0.02810000069439411,"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/wideband-audio","display_name":"Wideband audio","score":0.7706999778747559},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.7645999789237976},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5667999982833862},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.527999997138977},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5116000175476074},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.48240000009536743},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.47600001096725464},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.37369999289512634}],"concepts":[{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.7706999778747559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659000158309937},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.7645999789237976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6212999820709229},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5667999982833862},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.527999997138977},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5116000175476074},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.37220001220703125},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.36800000071525574},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.3443000018596649},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.32820001244544983},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C197477341","wikidata":"https://www.wikidata.org/wiki/Q2532845","display_name":"Full Rate","level":3,"score":0.29750001430511475},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C2778950570","wikidata":"https://www.wikidata.org/wiki/Q1466199","display_name":"Opus","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C200157131","wikidata":"https://www.wikidata.org/wiki/Q4854763","display_name":"Bandwidth allocation","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230955","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1519690927","https://openalex.org/W1601566090","https://openalex.org/W2135567392","https://openalex.org/W2167341025","https://openalex.org/W2750167318","https://openalex.org/W2895654193","https://openalex.org/W2929274168","https://openalex.org/W3025844872","https://openalex.org/W3092791109","https://openalex.org/W3198020407","https://openalex.org/W4221155904","https://openalex.org/W4372260387","https://openalex.org/W4386764386","https://openalex.org/W4387870028","https://openalex.org/W4388118256","https://openalex.org/W4392903975","https://openalex.org/W4392931427","https://openalex.org/W4402112435"],"related_works":[],"abstract_inverted_index":{"Reducing":[0],"the":[1,28,42,77,90,97,130,138,156,162],"bandwidth":[2,29,132,158,167],"of":[3,30,57,67,73,140,148,164],"speech":[4,14,32,43,86,100],"is":[5,35,79],"common":[6,84],"practice":[7],"in":[8,41,106],"resource":[9],"constrained":[10],"environments":[11],"like":[12],"low-bandwidth":[13],"transmission":[15],"or":[16],"low-complexity":[17],"vocoding.":[18],"We":[19,88,122],"propose":[20],"a":[21,55,64,71,107,171],"lightweight":[22],"and":[23,54,70,104,146],"robust":[24],"method":[25],"for":[26,81,173],"extending":[27],"wideband":[31,85],"signals":[33],"that":[34,112,125,147,155],"inspired":[36],"by":[37,93],"classical":[38,165],"methods":[39],"developed":[40],"coding":[44],"context.":[45],"The":[46],"resulting":[47],"model":[48,78],"has":[49],"just":[50],"\u223c370":[51],"K":[52],"parameters":[53],"complexity":[56],"\u223c140":[58],"MFLOPS":[59],"(or":[60],"\u223c70":[61],"MMACS).":[62],"With":[63],"frame":[65],"size":[66],"10":[68],"ms":[69],"lookahead":[72],"only":[74],"0.27":[75],"ms,":[76],"well-suited":[80],"use":[82],"with":[83,96,129],"codecs.":[87],"evaluate":[89],"model\u2019s":[91],"robustness":[92],"pairing":[94],"it":[95,113],"Opus":[98,126,149],"SILK":[99],"codec":[101],"(1.5":[102],"release)":[103],"verify":[105],"P.808":[108],"DCR":[109],"listening":[110],"test":[111],"significantly":[114],"improves":[115],"quality":[116,139,163,175],"from":[117],"6":[118],"to":[119],"12":[120],"kb/s.":[121],"also":[123],"demonstrate":[124],"1.5":[127],"together":[128],"proposed":[131],"extension":[133,159],"at":[134,143,151],"9":[135],"kb/s":[136,145,153],"meets":[137],"3GPP":[141],"EVS":[142],"9.6":[144],"1.4":[150],"18":[152],"showing":[154],"blind":[157],"can":[160],"meet":[161],"guided":[166],"extensions":[168],"thus":[169],"providing":[170],"way":[172],"backward-compatible":[174],"improvement.":[176]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}
