{"id":"https://openalex.org/W4406461488","doi":"https://doi.org/10.1109/slt61566.2024.10832364","title":"Codec-Superb @ SLT 2024: A Lightweight Benchmark For Neural Audio Codec Models","display_name":"Codec-Superb @ SLT 2024: A Lightweight Benchmark For Neural Audio Codec Models","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461488","doi":"https://doi.org/10.1109/slt61566.2024.10832364"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5101474128","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0001-7166-5534"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Haibin Wu","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083897242","display_name":"Xuanjun Chen","orcid":"https://orcid.org/0009-0002-5930-3797"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Xuanjun Chen","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105411292","display_name":"Yi\u2010Cheng Lin","orcid":"https://orcid.org/0009-0005-0969-631X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Cheng Lin","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073201681","display_name":"Kai\u2010Wei Chang","orcid":"https://orcid.org/0000-0002-4991-5274"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kaiwei Chang","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114129210","display_name":"Jiawei Du","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jiawei Du","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013041579","display_name":"Ke-Han Lu","orcid":"https://orcid.org/0000-0002-5331-0534"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ke-Han Lu","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064142365","display_name":"Alexander H. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander H. Liu","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111114748","display_name":"Ho-Lam Chung","orcid":"https://orcid.org/0000-0003-3847-0166"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ho-Lam Chung","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078327190","display_name":"Yuan-Kuei Wu","orcid":"https://orcid.org/0000-0002-3044-8709"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Kuei Wu","raw_affiliation_strings":["Meta","National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]},{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043555011","display_name":"Dongchao Yang","orcid":"https://orcid.org/0000-0002-8905-224X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dongchao Yang","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Songxiang Liu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003177601","display_name":"Yi-Chiao Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":["Meta","National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]},{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018286848","display_name":"Xu Tan","orcid":"https://orcid.org/0000-0001-6123-4378"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5101474128"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":2.293,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8980706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"570","last_page":"577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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":0.9998000264167786,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.940703272819519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7790228724479675},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6715372204780579},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.6416234970092773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5357377529144287},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.20787665247917175},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.12602588534355164},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.06503179669380188}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.940703272819519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7790228724479675},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6715372204780579},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.6416234970092773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5357377529144287},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.20787665247917175},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.12602588534355164},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.06503179669380188},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":72,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1567520911","https://openalex.org/W2030931454","https://openalex.org/W2052666245","https://openalex.org/W2067295501","https://openalex.org/W2320832475","https://openalex.org/W2726515241","https://openalex.org/W2803193013","https://openalex.org/W2972584841","https://openalex.org/W3024869864","https://openalex.org/W3027008958","https://openalex.org/W3036167779","https://openalex.org/W3139878283","https://openalex.org/W3161223924","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4205689591","https://openalex.org/W4285483774","https://openalex.org/W4300980117","https://openalex.org/W4307323391","https://openalex.org/W4311000453","https://openalex.org/W4313679638","https://openalex.org/W4318351475","https://openalex.org/W4372266552","https://openalex.org/W4372270198","https://openalex.org/W4372279529","https://openalex.org/W4377010126","https://openalex.org/W4379259581","https://openalex.org/W4380551955","https://openalex.org/W4381786045","https://openalex.org/W4386384714","https://openalex.org/W4392019360","https://openalex.org/W4392019859","https://openalex.org/W4392538788","https://openalex.org/W4392902628","https://openalex.org/W4392903089","https://openalex.org/W4392903389","https://openalex.org/W4392903801","https://openalex.org/W4392903887","https://openalex.org/W4392909975","https://openalex.org/W4392931975","https://openalex.org/W4399759291","https://openalex.org/W4399875170","https://openalex.org/W4399911677","https://openalex.org/W4402111239","https://openalex.org/W4402111789","https://openalex.org/W4402669711","https://openalex.org/W4402670057","https://openalex.org/W4404740148","https://openalex.org/W4406496863","https://openalex.org/W6777776875","https://openalex.org/W6779823529","https://openalex.org/W6840200333","https://openalex.org/W6845479124","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6849105126","https://openalex.org/W6852581948","https://openalex.org/W6853165267","https://openalex.org/W6853188576","https://openalex.org/W6853515095","https://openalex.org/W6855885476","https://openalex.org/W6856515471","https://openalex.org/W6859908464","https://openalex.org/W6861548716","https://openalex.org/W6861935630","https://openalex.org/W6862144568","https://openalex.org/W6869393727","https://openalex.org/W6869755106","https://openalex.org/W6912804647","https://openalex.org/W6948682473"],"related_works":["https://openalex.org/W4252424250","https://openalex.org/W2370747337","https://openalex.org/W1890500690","https://openalex.org/W2133351881","https://openalex.org/W2157819213","https://openalex.org/W2205640666","https://openalex.org/W2382399415","https://openalex.org/W2369511196","https://openalex.org/W2163719598","https://openalex.org/W4241950017"],"abstract_inverted_index":{"Neural":[0],"audio":[1,26,35],"codec":[2,27,45,51,82],"models":[3,46,52,83],"are":[4,53],"becoming":[5],"increasingly":[6],"important":[7],"as":[8,11],"they":[9],"serve":[10],"tokenizers":[12],"for":[13],"audio,":[14],"enabling":[15],"efficient":[16],"transmission":[17],"or":[18],"facilitating":[19],"speech":[20,95],"language":[21],"modeling.":[22],"The":[23],"ideal":[24],"neural":[25,44],"should":[28],"maintain":[29],"content,":[30],"paralinguistics,":[31],"speaker":[32],"characteristics,":[33],"and":[34,77,84,97,100,125],"information":[36],"even":[37],"at":[38,68],"low":[39],"bitrates.":[40],"Recently,":[41],"numerous":[42],"advanced":[43],"have":[47],"been":[48],"proposed.":[49],"However,":[50],"often":[54],"tested":[55],"under":[56],"varying":[57],"experimental":[58],"conditions.":[59],"As":[60],"a":[61],"result,":[62],"we":[63],"introduce":[64],"the":[65,88,118],"Codec-SUPERB":[66],"challenge":[67,91],"SLT":[69],"2024<sup":[70],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[71,127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[72],"designed":[73],"to":[74,110],"facilitate":[75],"fair":[76],"lightweight":[78],"comparisons":[79],"among":[80],"existing":[81],"inspire":[85],"advancements":[86],"in":[87],"field.":[89],"This":[90,115],"brings":[92],"together":[93],"representative":[94],"applications":[96],"objective":[98],"metrics,":[99],"carefully":[101],"selects":[102],"license-free":[103],"datasets,":[104,121],"sampling":[105],"them":[106],"into":[107],"small":[108],"sets":[109],"reduce":[111],"evaluation":[112],"computation":[113],"costs.":[114],"paper":[116],"presents":[117],"challenge\u2019s":[119],"rules,":[120],"participant":[122],"systems,":[123],"results,":[124],"findings.<sup":[126],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>https://codecsuperb.github.io/":[128]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}
