{"id":"https://openalex.org/W4224916783","doi":"https://doi.org/10.1109/icassp43922.2022.9747527","title":"Progressive Multi-Stage Neural Audio Coding with Guided References","display_name":"Progressive Multi-Stage Neural Audio Coding with Guided References","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224916783","doi":"https://doi.org/10.1109/icassp43922.2022.9747527"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747527","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5061446062","display_name":"Chanwoo Lee","orcid":"https://orcid.org/0000-0001-7630-2927"},"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":"Chanwoo 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/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 Institution,Daejeon,South Korea","Electronics and Telecommunications Research Institution, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institution,Daejeon,South Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Electronics and Telecommunications Research Institution, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"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/A5061446062"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":1.2273,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81105845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"876","last_page":"880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9979000091552734,"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/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7828162312507629},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7669672966003418},{"id":"https://openalex.org/keywords/decodes","display_name":"Decodes","score":0.7506864070892334},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.710229218006134},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.695917546749115},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6940242648124695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6775565147399902},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.557641327381134},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5147533416748047},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5007715225219727},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.4781395196914673},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4686999022960663},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4647819995880127},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.46072107553482056},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4323301911354065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4096137285232544},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.25592708587646484},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2518690228462219},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16546732187271118},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16128823161125183},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11560714244842529},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09485504031181335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828162312507629},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7669672966003418},{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.7506864070892334},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.710229218006134},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.695917546749115},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6940242648124695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6775565147399902},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.557641327381134},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5147533416748047},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5007715225219727},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.4781395196914673},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4686999022960663},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4647819995880127},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.46072107553482056},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4323301911354065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4096137285232544},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25592708587646484},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2518690228462219},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16546732187271118},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16128823161125183},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11560714244842529},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09485504031181335},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747527","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"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":28,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1523644733","https://openalex.org/W1703292843","https://openalex.org/W2016589492","https://openalex.org/W2476548250","https://openalex.org/W2593414223","https://openalex.org/W2732044853","https://openalex.org/W2752796333","https://openalex.org/W2908510526","https://openalex.org/W2963182577","https://openalex.org/W2963799213","https://openalex.org/W2964024144","https://openalex.org/W2972354707","https://openalex.org/W3037038648","https://openalex.org/W3092028330","https://openalex.org/W3110277971","https://openalex.org/W3144035034","https://openalex.org/W3215615641","https://openalex.org/W4205788663","https://openalex.org/W4294643831","https://openalex.org/W6621543089","https://openalex.org/W6631257896","https://openalex.org/W6639363673","https://openalex.org/W6741057705","https://openalex.org/W6745560452","https://openalex.org/W6757817989","https://openalex.org/W6783867762","https://openalex.org/W6798098866"],"related_works":["https://openalex.org/W2060409740","https://openalex.org/W2374470469","https://openalex.org/W2106164298","https://openalex.org/W2369063343","https://openalex.org/W2122456865","https://openalex.org/W2115984063","https://openalex.org/W2129913000","https://openalex.org/W2383697325","https://openalex.org/W2121846146","https://openalex.org/W2092228680"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,35],"propose":[4],"an":[5,22,72,106],"effective":[6,73],"multi-stage":[7,74],"neural":[8],"audio":[9,15,39,63,68,99],"coding":[10],"algorithm":[11],"that":[12,45,92],"encodes":[13],"full-band":[14,67],"signals":[16,31,40,69],"(up":[17],"to":[18,78],"20":[19],"kHz)":[20],"using":[21,71],"end-to-end":[23],"training":[24,33],"criterion.":[25],"By":[26],"predefining":[27],"several":[28],"dyadic":[29],"subband":[30],"as":[32],"targets,":[34],"progressively":[36],"encode":[37,51],"input":[38],"in":[41,84],"each":[42],"stage":[43],"such":[44],"deeper":[46],"stages":[47],"of":[48,96,109],"the":[49,52,57,85,93,97],"network":[50],"residual":[53],"error":[54],"terms":[55],"from":[56],"previous":[58],"encoding":[59,81],"stage.":[60],"Our":[61],"proposed":[62,98],"codec":[64,100],"successfully":[65],"decodes":[66],"by":[70],"vector":[75],"quantization":[76],"scheme":[77],"represent":[79],"key":[80],"features":[82],"extracted":[83],"latent":[86],"space.":[87],"Subjective":[88],"listening":[89],"tests":[90],"show":[91],"decoded":[94],"outputs":[95],"achieve":[101],"almost":[102],"transparent":[103],"quality":[104],"at":[105],"average":[107],"bitrate":[108],"132":[110],"kbps.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
