{"id":"https://openalex.org/W4402915905","doi":"https://doi.org/10.1109/jstsp.2024.3469530","title":"HILCodec: High-Fidelity and Lightweight Neural Audio Codec","display_name":"HILCodec: High-Fidelity and Lightweight Neural Audio Codec","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915905","doi":"https://doi.org/10.1109/jstsp.2024.3469530"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2024.3469530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2024.3469530","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5103176510","display_name":"Sunghwan Ahn","orcid":"https://orcid.org/0009-0001-6799-6821"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunghwan Ahn","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0001-6799-6821","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003903797","display_name":"Beom Jun Woo","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Beom Jun Woo","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009851092","display_name":"Min Hyun Han","orcid":"https://orcid.org/0000-0002-8086-5009"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Min Hyun Han","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8086-5009","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097357647","display_name":"Chanyeong Moon","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanyeong Moon","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0005-9047-5353","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0568-4902","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0403,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92537925,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"18","issue":"8","first_page":"1517","last_page":"1530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9936000108718872,"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":0.9936000108718872,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.958899974822998,"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":0.9571999907493591,"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/codec","display_name":"Codec","score":0.8481982946395874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.816235363483429},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.532236635684967},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5166699886322021},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.47690463066101074},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.475117027759552},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.43367695808410645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38213402032852173},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35129043459892273},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.21658626198768616},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.18678447604179382},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.15610453486442566},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08234143257141113}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8481982946395874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816235363483429},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.532236635684967},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5166699886322021},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.47690463066101074},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.475117027759552},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.43367695808410645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38213402032852173},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35129043459892273},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.21658626198768616},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.18678447604179382},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.15610453486442566},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08234143257141113},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2024.3469530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2024.3469530","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W1677182931","https://openalex.org/W1966264494","https://openalex.org/W2079985975","https://openalex.org/W2106164298","https://openalex.org/W2110474886","https://openalex.org/W2128301448","https://openalex.org/W2129913307","https://openalex.org/W2131738223","https://openalex.org/W2139862710","https://openalex.org/W2151825755","https://openalex.org/W2166816543","https://openalex.org/W2172065531","https://openalex.org/W2194775991","https://openalex.org/W2752796333","https://openalex.org/W2775336875","https://openalex.org/W2791686384","https://openalex.org/W2963091184","https://openalex.org/W2963182577","https://openalex.org/W2963300588","https://openalex.org/W2963855133","https://openalex.org/W2981613960","https://openalex.org/W2998733532","https://openalex.org/W3015338123","https://openalex.org/W3015780049","https://openalex.org/W3037038648","https://openalex.org/W3095095816","https://openalex.org/W3163243746","https://openalex.org/W3197273793","https://openalex.org/W3215615641","https://openalex.org/W4206534210","https://openalex.org/W4214634256","https://openalex.org/W4224929672","https://openalex.org/W4225860133","https://openalex.org/W4225905067","https://openalex.org/W4238404964","https://openalex.org/W4244017338","https://openalex.org/W4245284779","https://openalex.org/W4254592580","https://openalex.org/W4307323391","https://openalex.org/W4372270198","https://openalex.org/W4382202681","https://openalex.org/W4385823460","https://openalex.org/W4392902628","https://openalex.org/W4392903389","https://openalex.org/W6631257896","https://openalex.org/W6635150655","https://openalex.org/W6659544808","https://openalex.org/W6685562342","https://openalex.org/W6695676441","https://openalex.org/W6737664043","https://openalex.org/W6739448629","https://openalex.org/W6745245109","https://openalex.org/W6748409065","https://openalex.org/W6757468910","https://openalex.org/W6763945542","https://openalex.org/W6767111847","https://openalex.org/W6772349387","https://openalex.org/W6774776664","https://openalex.org/W6779724054","https://openalex.org/W6780226713","https://openalex.org/W6780365925","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6784291726","https://openalex.org/W6788627230","https://openalex.org/W6802517614","https://openalex.org/W6838843145","https://openalex.org/W6843673214","https://openalex.org/W6852581948","https://openalex.org/W6853515095"],"related_works":["https://openalex.org/W4252424250","https://openalex.org/W2370747337","https://openalex.org/W1890500690","https://openalex.org/W2157819213","https://openalex.org/W2374470469","https://openalex.org/W2899318368","https://openalex.org/W2363660481","https://openalex.org/W2352448339","https://openalex.org/W2159899134","https://openalex.org/W2787189739"],"abstract_inverted_index":{"The":[0,97],"recent":[1],"advancement":[2],"of":[3,31,44,54,72],"end-to-end":[4],"neural":[5,46],"audio":[6,10,19,47,107,117],"codecs":[7],"enables":[8],"compressing":[9],"at":[11,28],"very":[12],"low":[13],"bitrates":[14,115],"while":[15],"reconstructing":[16],"the":[17,29,42,52,55,63,69],"output":[18],"with":[20],"high":[21],"fidelity.":[22],"Nonetheless,":[23],"such":[24,73],"improvements":[25],"often":[26],"come":[27],"cost":[30],"increased":[32],"model":[33],"complexity.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,82],"identify":[39],"and":[40,76,91,116],"address":[41],"problems":[43],"existing":[45],"codecs.":[48],"We":[49,67],"show":[50],"that":[51,109],"performance":[53],"SEANet-based":[56],"codec":[57,108],"does":[58],"not":[59],"increase":[60],"consistently":[61],"as":[62],"network":[64],"depth":[65],"increases.":[66],"analyze":[68],"root":[70],"cause":[71],"a":[74,78,93,104],"phenomenon":[75],"suggest":[77],"variance-constrained":[79],"design.":[80],"Also,":[81],"reveal":[83],"various":[84,114],"distortions":[85],"in":[86],"previous":[87],"waveform":[88],"domain":[89],"discriminators":[90],"propose":[92],"novel":[94],"distortion-free":[95],"discriminator.":[96],"resulting":[98],"model,":[99],"<italic":[100],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[101],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">HILCodec</i>,":[102],"is":[103],"real-time":[105],"streaming":[106],"demonstrates":[110],"state-of-the-art":[111],"quality":[112],"across":[113],"types.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}