{"id":"https://openalex.org/W4392902628","doi":"https://doi.org/10.1109/icassp48485.2024.10447532","title":"LightCodec: A High Fidelity Neural Audio Codec with Low Computation Complexity","display_name":"LightCodec: A High Fidelity Neural Audio Codec with Low Computation Complexity","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902628","doi":"https://doi.org/10.1109/icassp48485.2024.10447532"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5040488464","display_name":"Liang Xu","orcid":"https://orcid.org/0000-0002-4952-7300"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liang Xu","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China","School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378418","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-0149-2049"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China","School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040549851","display_name":"Jianqian Zhang","orcid":"https://orcid.org/0009-0000-3949-2549"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqian Zhang","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China","School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100642395","display_name":"Xiang Xie","orcid":"https://orcid.org/0000-0002-5135-0110"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Xie","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China","School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040488464"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":3.6216,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93540011,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"586","last_page":"590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9990000128746033,"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/codec","display_name":"Codec","score":0.9249234199523926},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8165044188499451},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.6978780031204224},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.6735224723815918},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5726609230041504},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5158421397209167},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5008163452148438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4980895519256592},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4561769664287567},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4194839894771576},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4175110459327698},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28500276803970337},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2705156207084656},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2123430371284485},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16185447573661804},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.1167965829372406},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08087316155433655}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.9249234199523926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165044188499451},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.6978780031204224},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.6735224723815918},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5726609230041504},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5158421397209167},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5008163452148438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4980895519256592},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4561769664287567},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4194839894771576},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4175110459327698},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28500276803970337},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2705156207084656},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2123430371284485},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16185447573661804},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.1167965829372406},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08087316155433655},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2064675550","https://openalex.org/W2752796333","https://openalex.org/W2963799213","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W2972519044","https://openalex.org/W2998572311","https://openalex.org/W3015338123","https://openalex.org/W3037038648","https://openalex.org/W3092028330","https://openalex.org/W3094002217","https://openalex.org/W3144035034","https://openalex.org/W3163662330","https://openalex.org/W3188073270","https://openalex.org/W3215615641","https://openalex.org/W4212774754","https://openalex.org/W4225287045","https://openalex.org/W4284972581","https://openalex.org/W4297841527","https://openalex.org/W4297841531","https://openalex.org/W4307323391","https://openalex.org/W4372279529","https://openalex.org/W4375869380","https://openalex.org/W6762931180","https://openalex.org/W6767111847","https://openalex.org/W6783867762","https://openalex.org/W6785090365","https://openalex.org/W6852581948"],"related_works":["https://openalex.org/W2374470469","https://openalex.org/W2129913000","https://openalex.org/W2899318368","https://openalex.org/W2363660481","https://openalex.org/W2352448339","https://openalex.org/W2159899134","https://openalex.org/W2787189739","https://openalex.org/W1980698970","https://openalex.org/W3095556352","https://openalex.org/W1745769461"],"abstract_inverted_index":{"The":[0,129],"audio":[1,10,22,71,135],"codec":[2,72],"is":[3,57,73,93,96,156],"one":[4],"of":[5,18,40,47,80,140],"the":[6,16,38,45,54,77,81,108,113,124,142,154],"core":[7],"modules":[8],"in":[9],"communication":[11],"for":[12,134],"real-time":[13],"transmission.":[14],"With":[15],"development":[17],"neural":[19,34],"networks,":[20],"end-to-end":[21],"codecs":[23,36],"have":[24,37],"emerged":[25],"and":[26,44,111,153],"demonstrated":[27],"effects":[28],"beyond":[29],"conventional":[30],"codecs.":[31],"However,":[32],"current":[33],"network-based":[35],"weakness":[39],"high":[41,84],"computational":[42,64],"complexity,":[43,55],"performance":[46,146],"these":[48],"methods":[49],"decreases":[50],"rapidly":[51],"after":[52],"decreasing":[53],"which":[56,95,122],"not":[58],"conducive":[59],"to":[60,106,150],"deployment":[61],"under":[62],"low":[63,78],"resources.":[65],"In":[66],"this":[67],"paper,":[68],"a":[69,86,99,118,137],"low-complexity":[70],"proposed.":[74],"To":[75],"realize":[76],"complexity":[79,155],"model":[82,143],"with":[83,136],"quality,":[85],"structure":[87],"based":[88],"on":[89],"frequency":[90],"band":[91,102],"division":[92],"designed,":[94],"implemented":[97],"using":[98],"within":[100,112],"bandacross":[101],"interaction":[103],"(WBABI)":[104],"module":[105],"learn":[107],"features":[109],"across":[110],"subband.":[114],"Further,":[115],"we":[116],"propose":[117],"new":[119],"quantization-compensation":[120],"module,":[121],"reduces":[123],"quantization":[125],"error":[126],"by":[127],"90%.":[128],"experimental":[130],"results":[131],"show":[132],"that":[133],"sample":[138],"rate":[139],"24kHz,":[141],"shows":[144],"excellent":[145],"at":[147],"3~6kbps":[148],"compared":[149],"other":[151],"codecs,":[152],"only":[157],"0.8":[158],"Giga":[159],"Multiply-Add":[160],"Operations":[161],"per":[162],"Second(GMACs).":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}