{"id":"https://openalex.org/W4372267315","doi":"https://doi.org/10.1109/icassp49357.2023.10097001","title":"Progressive Multi-Stage Neural Audio Codec with Psychoacoustic Loss and Discriminator","display_name":"Progressive Multi-Stage Neural Audio Codec with Psychoacoustic Loss and Discriminator","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267315","doi":"https://doi.org/10.1109/icassp49357.2023.10097001"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097001","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097001","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/A5034035652","display_name":"Byeong Hyeon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Byeong Hyeon Kim","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075112605","display_name":"Hyungseob Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungseob Lim","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413513","display_name":"Ji\u2010Hyun Lee","orcid":"https://orcid.org/0000-0002-9864-5485"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihyun Lee","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"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","Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute,Daejeon,South Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101203935","display_name":"Hong-Goo Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5034035652"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":1.0189,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74785603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"2","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":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7635784149169922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7581645250320435},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7224499583244324},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6683418154716492},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5937431454658508},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.5478224754333496},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5400320887565613},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.501072883605957},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.44691476225852966},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.43568602204322815},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.42670533061027527},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.4154571294784546},{"id":"https://openalex.org/keywords/companding","display_name":"Companding","score":0.41384610533714294},{"id":"https://openalex.org/keywords/bitstream","display_name":"Bitstream","score":0.411074161529541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.408134400844574},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2514701187610626},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22216108441352844},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.21083134412765503},{"id":"https://openalex.org/keywords/orthogonal-frequency-division-multiplexing","display_name":"Orthogonal frequency-division multiplexing","score":0.14696121215820312},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11391335725784302},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10962092876434326}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7635784149169922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581645250320435},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7224499583244324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6683418154716492},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5937431454658508},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.5478224754333496},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5400320887565613},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.501072883605957},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.44691476225852966},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.43568602204322815},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.42670533061027527},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4154571294784546},{"id":"https://openalex.org/C104250799","wikidata":"https://www.wikidata.org/wiki/Q1780765","display_name":"Companding","level":4,"score":0.41384610533714294},{"id":"https://openalex.org/C136695289","wikidata":"https://www.wikidata.org/wiki/Q415568","display_name":"Bitstream","level":3,"score":0.411074161529541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.408134400844574},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2514701187610626},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22216108441352844},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.21083134412765503},{"id":"https://openalex.org/C40409654","wikidata":"https://www.wikidata.org/wiki/Q375889","display_name":"Orthogonal frequency-division multiplexing","level":3,"score":0.14696121215820312},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11391335725784302},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10962092876434326},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097001","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097001","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7699999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1577841048","https://openalex.org/W1600046928","https://openalex.org/W2106164298","https://openalex.org/W2128301448","https://openalex.org/W2552465432","https://openalex.org/W2593414223","https://openalex.org/W2962676454","https://openalex.org/W2963182577","https://openalex.org/W2972354707","https://openalex.org/W2998733532","https://openalex.org/W3092028330","https://openalex.org/W3110277971","https://openalex.org/W3145029257","https://openalex.org/W3172592779","https://openalex.org/W3197273793","https://openalex.org/W3215615641","https://openalex.org/W4224916783","https://openalex.org/W4224919007","https://openalex.org/W6634650089","https://openalex.org/W6635978488","https://openalex.org/W6783867762","https://openalex.org/W6793364766"],"related_works":["https://openalex.org/W2892072280","https://openalex.org/W2130095015","https://openalex.org/W3034731095","https://openalex.org/W2996518094","https://openalex.org/W2364915322","https://openalex.org/W1485474031","https://openalex.org/W2185350064","https://openalex.org/W2789044730","https://openalex.org/W2181640205","https://openalex.org/W2357565948"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,53],"improve":[4],"the":[5,8,32,77,94,111,114,118],"efficiency":[6],"of":[7,113],"progressive":[9],"multi-stage":[10],"neural":[11],"audio":[12,74],"codec":[13],"(PR-Codec)":[14],"by":[15,29],"utilizing":[16],"perceptually":[17,50,78],"motivated":[18,79],"training":[19],"criteria.":[20],"Although":[21],"our":[22,102,122],"baseline":[23],"PR-Codec":[24],"successfully":[25],"reconstructs":[26],"full-band":[27],"signals":[28,75],"progressively":[30],"decoding":[31],"pre-defined":[33],"subband":[34],"signals,":[35],"transparent":[36,51],"quality":[37,109],"can":[38],"only":[39],"be":[40],"guaranteed":[41],"in":[42,76,117],"high":[43],"bit-rates.":[44],"To":[45],"reduce":[46],"bit-rates":[47],"while":[48],"maintaining":[49],"quality,":[52],"adopt":[54],"a":[55,62,84],"psychoacoustic":[56],"model":[57,90,104],"(PAM)-based":[58],"loss":[59],"and":[60,72],"propose":[61],"perceptual":[63,107],"weighting":[64],"discriminator":[65],"(PWD),":[66],"which":[67],"enables":[68],"us":[69],"to":[70,91,121],"synthesize":[71],"discriminate":[73],"domain.":[80],"We":[81],"also":[82],"introduce":[83],"scalar":[85],"quantization":[86,95],"with":[87],"an":[88],"entropy":[89],"further":[92],"enhance":[93],"efficiency.":[96],"Our":[97],"experimental":[98],"results":[99],"show":[100],"that":[101],"proposed":[103],"significantly":[105],"improves":[106],"reconstruction":[108],"at":[110],"expense":[112],"waveform":[115],"disparity":[116],"time-domain,":[119],"compared":[120],"previous":[123],"model.":[124]},"counts_by_year":[{"year":2024,"cited_by_count":5}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}