{"id":"https://openalex.org/W4405974781","doi":"https://doi.org/10.1109/msp.2024.3444318","title":"Neural Speech and Audio Coding: Modern AI technology meets traditional codecs","display_name":"Neural Speech and Audio Coding: Modern AI technology meets traditional codecs","publication_year":2024,"publication_date":"2024-11-01","ids":{"openalex":"https://openalex.org/W4405974781","doi":"https://doi.org/10.1109/msp.2024.3444318"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2024.3444318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2024.3444318","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"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 Signal Processing Magazine","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/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minje Kim","raw_affiliation_strings":["University of Illinois at Urba-na-Champaign, Champaign, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-3513-8328","affiliations":[{"raw_affiliation_string":"University of Illinois at Urba-na-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070792118","display_name":"Jan Skoglund","orcid":"https://orcid.org/0009-0008-0167-4628"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Skoglund","raw_affiliation_strings":["Google LLC, San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0009-0008-0167-4628","affiliations":[{"raw_affiliation_string":"Google LLC, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064582903"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":2.6491,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91545148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"41","issue":"6","first_page":"85","last_page":"93"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.955299973487854,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.955299973487854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7926271557807922},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.7891170382499695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7070144414901733},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6977245807647705},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.6151849031448364},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.5910219550132751},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5829731225967407},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5502660870552063},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.5223175883293152},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5099033117294312},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4798573851585388},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.43584734201431274},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4357619881629944},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3928880989551544},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.2205202281475067},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2003782093524933},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.12220233678817749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926271557807922},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.7891170382499695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7070144414901733},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6977245807647705},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.6151849031448364},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.5910219550132751},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5829731225967407},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5502660870552063},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.5223175883293152},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5099033117294312},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4798573851585388},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.43584734201431274},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4357619881629944},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3928880989551544},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.2205202281475067},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2003782093524933},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.12220233678817749},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msp.2024.3444318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2024.3444318","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"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 Signal Processing Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7696974451","display_name":null,"funder_award_id":"24ZC1100","funder_id":"https://openalex.org/F4320322093","funder_display_name":"Electronics and Telecommunications Research Institute"}],"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":28,"referenced_works":["https://openalex.org/W2128301448","https://openalex.org/W2157331557","https://openalex.org/W2165291881","https://openalex.org/W2519091744","https://openalex.org/W2775336875","https://openalex.org/W2809824582","https://openalex.org/W2935711438","https://openalex.org/W2944209089","https://openalex.org/W2963182577","https://openalex.org/W2972354707","https://openalex.org/W2972519044","https://openalex.org/W3015780049","https://openalex.org/W3110277971","https://openalex.org/W3197776431","https://openalex.org/W3214758449","https://openalex.org/W3215615641","https://openalex.org/W4206319965","https://openalex.org/W4225860133","https://openalex.org/W4250212848","https://openalex.org/W4256390999","https://openalex.org/W4319347033","https://openalex.org/W4372190822","https://openalex.org/W4372260101","https://openalex.org/W4372348514","https://openalex.org/W4377231659","https://openalex.org/W6741057705","https://openalex.org/W6748409065","https://openalex.org/W6853515095"],"related_works":["https://openalex.org/W2060409740","https://openalex.org/W2159307410","https://openalex.org/W2370747337","https://openalex.org/W2121846146","https://openalex.org/W137020845","https://openalex.org/W1542588102","https://openalex.org/W2496295964","https://openalex.org/W2151333624","https://openalex.org/W2020464095","https://openalex.org/W2336887028"],"abstract_inverted_index":{"This":[0],"article":[1,115,151],"explores":[2],"the":[3,11,22,26,37,51,69,97,114,134,150,153,160,169],"integration":[4],"of":[5,13,30,39,53,71,136,155,162],"model-based":[6,54,173],"and":[7,16,32,35,101,132,164,175],"data-driven":[8,41,177],"approaches":[9,174],"within":[10,122],"realm":[12],"neural":[14,83,111,144],"speech":[15,31,163],"audio":[17,33,145,165],"coding":[18,108,166],"systems.":[19],"It":[20],"highlights":[21],"challenges":[23],"posed":[24],"by":[25,167],"subjective":[27],"evaluation":[28],"processes":[29],"codecs":[34,73],"discusses":[36],"limitations":[38],"purely":[40],"approaches,":[42],"which":[43],"often":[44],"require":[45],"inefficiently":[46],"large":[47],"architectures":[48],"to":[49,68,90,141,158],"match":[50],"performance":[52,70],"methods.":[55],"The":[56],"study":[57],"presents":[58],"hybrid":[59,156],"systems":[60,103,157],"as":[61],"a":[62,82],"viable":[63],"solution,":[64],"offering":[65],"significant":[66],"improvements":[67],"conventional":[72],"through":[74],"meticulously":[75],"chosen":[76],"design":[77],"enhancements.":[78],"Specifically,":[79],"it":[80],"introduces":[81],"network-based":[84],"signal":[85],"enhancer":[86],"that":[87,104,120],"is":[88],"designed":[89],"postprocess":[91],"existing":[92],"codecs\u2019":[93],"output,":[94],"along":[95],"with":[96,110],"autoencoder-based":[98],"end-to-end":[99,143],"models":[100,119],"LPCNet\u2013hybrid":[102],"combine":[105],"linear":[106],"predictive":[107,118],"(LPC)":[109],"networks.":[112],"Furthermore,":[113],"delves":[116],"into":[117],"operate":[121],"custom":[123],"feature":[124],"spaces":[125],"(TF-Codec)":[126],"or":[127],"predefined":[128],"transform":[129],"domains":[130],"(MDCTNet)":[131],"examines":[133],"use":[135],"psychoacoustically":[137],"calibrated":[138],"loss":[139],"functions":[140],"train":[142],"codecs.":[146],"Through":[147],"these":[148],"investigations,":[149],"demonstrates":[152],"potential":[154],"advance":[159],"field":[161],"bridging":[168],"gap":[170],"between":[171],"traditional":[172],"modern":[176],"techniques.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-01-02T00:00:00"}