{"id":"https://openalex.org/W4372262417","doi":"https://doi.org/10.1109/icassp49357.2023.10094593","title":"Native Multi-Band Audio Coding Within Hyper-Autoencoded Reconstruction Propagation Networks","display_name":"Native Multi-Band Audio Coding Within Hyper-Autoencoded Reconstruction Propagation Networks","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372262417","doi":"https://doi.org/10.1109/icassp49357.2023.10094593"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094593","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094593","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":"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/A5018337836","display_name":"Darius Petermann","orcid":"https://orcid.org/0000-0002-5973-5752"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Darius Petermann","raw_affiliation_strings":["Indiana University,Department of Intelligent Systems Engineering,Bloomington,IN,USA,47408"],"affiliations":[{"raw_affiliation_string":"Indiana University,Department of Intelligent Systems Engineering,Bloomington,IN,USA,47408","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059001612","display_name":"Inseon Jang","orcid":"https://orcid.org/0000-0003-2237-2668"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inseon Jang","raw_affiliation_strings":["Electronics and Telecommunications Research Institute,Daejeon,South Korea,34129"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute,Daejeon,South Korea,34129","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Indiana University,Department of Intelligent Systems Engineering,Bloomington,IN,USA,47408"],"affiliations":[{"raw_affiliation_string":"Indiana University,Department of Intelligent Systems Engineering,Bloomington,IN,USA,47408","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018337836"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":0.2033,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39894849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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":0.9998000264167786,"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":0.9998000264167786,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9987999796867371,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.786377489566803},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.7774479389190674},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6831173300743103},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5622187256813049},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5497638583183289},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4496973156929016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4210840165615082},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4077465236186981},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3789738416671753},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.22641828656196594},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10600268840789795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786377489566803},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.7774479389190674},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6831173300743103},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5622187256813049},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5497638583183289},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4496973156929016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4210840165615082},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4077465236186981},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3789738416671753},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.22641828656196594},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10600268840789795},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094593","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094593","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":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1653357422","https://openalex.org/W1901129140","https://openalex.org/W1963699091","https://openalex.org/W2128301448","https://openalex.org/W2163509604","https://openalex.org/W2168230675","https://openalex.org/W2519091744","https://openalex.org/W2566983320","https://openalex.org/W2620812332","https://openalex.org/W2732044853","https://openalex.org/W2775336875","https://openalex.org/W2929274168","https://openalex.org/W2935711438","https://openalex.org/W2936557804","https://openalex.org/W2963182577","https://openalex.org/W2998639482","https://openalex.org/W3015567712","https://openalex.org/W3110277971","https://openalex.org/W3160652646","https://openalex.org/W3162366763","https://openalex.org/W3186609711","https://openalex.org/W3215615641","https://openalex.org/W4285186333","https://openalex.org/W4296068998","https://openalex.org/W4307323391","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6684410015","https://openalex.org/W6731445010","https://openalex.org/W6741057705"],"related_works":["https://openalex.org/W2374470469","https://openalex.org/W2352448339","https://openalex.org/W2787189739","https://openalex.org/W2011561032","https://openalex.org/W2899318368","https://openalex.org/W3095556352","https://openalex.org/W2363660481","https://openalex.org/W2159899134","https://openalex.org/W2091360050","https://openalex.org/W2027103574"],"abstract_inverted_index":{"Spectral":[0],"sub-bands":[1],"do":[2],"not":[3,129],"portray":[4],"the":[5,23,58,65,85,90,106,111,126,132,135,151],"same":[6],"perceptual":[7],"relevance.":[8],"In":[9,37],"audio":[10,45,117],"coding,":[11],"it":[12,144],"is":[13],"therefore":[14,94],"desirable":[15],"to":[16,102,115,143],"have":[17],"independent":[18,70],"control":[19,71],"over":[20,72],"each":[21],"of":[22,60,134],"constituent":[24],"bands":[25],"so":[26],"that":[27,48,125],"bitrate":[28],"assignment":[29],"and":[30,75,79,96],"signal":[31,87],"reconstruction":[32,113],"can":[33],"be":[34],"achieved":[35],"efficiently.":[36],"this":[38],"work,":[39],"we":[40],"present":[41],"a":[42,51,147],"novel":[43],"neural":[44],"coding":[46,53],"network":[47],"natively":[49],"supports":[50],"multi-band":[52],"paradigm.":[54],"Our":[55,82],"model":[56,128],"extends":[57],"idea":[59],"compressed":[61],"skip":[62],"connections":[63],"in":[64,150],"U-Net-based":[66],"codec,":[67],"allowing":[68],"for":[69],"both":[73],"core":[74,136],"high":[76],"band-specific":[77],"reconstructions":[78],"bit":[80],"allocation.":[81],"system":[83],"reconstructs":[84],"full-band":[86],"mainly":[88],"from":[89],"condensed":[91],"core-band":[92],"code,":[93],"exploiting":[95],"showcasing":[97],"its":[98,103],"bandwidth":[99,120],"extension":[100],"capabilities":[101],"fullest.":[104],"Meanwhile,":[105],"low-bitrate":[107],"high-band":[108,112,152],"code":[109],"helps":[110],"similarly":[114],"MPEG":[116],"codecs'":[118],"spectral":[119],"replication.":[121],"MUSHRA":[122],"tests":[123],"show":[124],"proposed":[127],"only":[130],"improves":[131],"quality":[133,149],"band":[137],"by":[138],"explicitly":[139],"assigning":[140],"more":[141],"bits":[142],"but":[145],"retains":[146],"good":[148],"as":[153],"well.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}
