{"id":"https://openalex.org/W4399875170","doi":"https://doi.org/10.1109/taslp.2024.3417347","title":"APCodec: A Neural Audio Codec With Parallel Amplitude and Phase Spectrum Encoding and Decoding","display_name":"APCodec: A Neural Audio Codec With Parallel Amplitude and Phase Spectrum Encoding and Decoding","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399875170","doi":"https://doi.org/10.1109/taslp.2024.3417347"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3417347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3417347","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language 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/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6668-022X","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031429152","display_name":"Xiao-Hang Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Hang Jiang","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072371384","display_name":"Ye-Xin Lu","orcid":"https://orcid.org/0009-0009-8026-0702"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye-Xin Lu","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0009-8026-0702","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067982618","display_name":"Hui-Peng Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui-Peng Du","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":10.1356,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.98948068,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"3256","last_page":"3269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9983999729156494,"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/T10320","display_name":"Neural Networks and Applications","score":0.9983000159263611,"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":0.783329427242279},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7172365188598633},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6888372898101807},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5975505113601685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.567924439907074},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.49898529052734375},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.47647735476493835},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.47069525718688965},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4458846151828766},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.22122743725776672},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1897960603237152},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12732332944869995},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.11345657706260681},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.06843280792236328}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.783329427242279},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7172365188598633},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6888372898101807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5975505113601685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.567924439907074},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.49898529052734375},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.47647735476493835},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.47069525718688965},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4458846151828766},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.22122743725776672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1897960603237152},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12732332944869995},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.11345657706260681},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.06843280792236328},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3417347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3417347","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1080972157","display_name":null,"funder_award_id":"WK2100000033","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2545034164","display_name":null,"funder_award_id":"2308085QF200","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G2883670753","display_name":null,"funder_award_id":"U23B2053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5861301885","display_name":null,"funder_award_id":"62301521","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W1553834069","https://openalex.org/W1989395836","https://openalex.org/W2020883660","https://openalex.org/W2067295501","https://openalex.org/W2130158387","https://openalex.org/W2131738223","https://openalex.org/W2159644785","https://openalex.org/W2168098717","https://openalex.org/W2752796333","https://openalex.org/W2775336875","https://openalex.org/W2899663614","https://openalex.org/W2935711438","https://openalex.org/W2963182577","https://openalex.org/W2963208781","https://openalex.org/W2964073500","https://openalex.org/W2972354707","https://openalex.org/W2972519044","https://openalex.org/W2998572311","https://openalex.org/W3037038648","https://openalex.org/W3188073270","https://openalex.org/W3197273793","https://openalex.org/W3215615641","https://openalex.org/W4205689591","https://openalex.org/W4296068763","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4372260101","https://openalex.org/W4372260247","https://openalex.org/W4372270198","https://openalex.org/W4372279529","https://openalex.org/W4375869380","https://openalex.org/W4375869436","https://openalex.org/W4377000449","https://openalex.org/W4381786045","https://openalex.org/W4385822716","https://openalex.org/W4385823076","https://openalex.org/W4385823460","https://openalex.org/W4386076493","https://openalex.org/W4386384714","https://openalex.org/W4392903006","https://openalex.org/W4402672068","https://openalex.org/W4405521053","https://openalex.org/W6630442970","https://openalex.org/W6633114069","https://openalex.org/W6755977528","https://openalex.org/W6757817989","https://openalex.org/W6767111847","https://openalex.org/W6771467084","https://openalex.org/W6772349387","https://openalex.org/W6780226713","https://openalex.org/W6783867762","https://openalex.org/W6848735303","https://openalex.org/W6852581948","https://openalex.org/W6853515095","https://openalex.org/W6855885476","https://openalex.org/W6856524194","https://openalex.org/W6859898589"],"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":{"This":[0,107],"paper":[1],"introduces":[2],"a":[3,61,74,98,103,182],"novel":[4],"neural":[5],"audio":[6,35,48,88,120,144,205,234],"codec":[7],"targeting":[8],"high":[9],"waveform":[10,27,130,146],"sampling":[11],"rates":[12],"and":[13,26,37,44,60,90,122,127,152,175,236,248],"low":[14],"bitrates":[15],"named":[16],"APCodec,":[17,180],"which":[18],"seamlessly":[19],"integrates":[20],"the":[21,32,42,64,70,78,87,113,116,119,128,140,164,189,217,220,224],"strengths":[22],"of":[23,34,57,142,191,208,219],"parametric":[24,49,52],"codecs":[25],"codecs.":[28,53],"The":[29,84],"APCodec":[30,200,229],"revolutionizes":[31],"process":[33],"encoding":[36],"decoding":[38],"by":[39,73,112,133],"concurrently":[40],"handling":[41],"amplitude":[43,89,121],"phase":[45,91,123],"spectra":[46,92,124],"as":[47,69,245],"characteristics":[50],"like":[51,145],"It":[54],"is":[55,109,131],"composed":[56],"an":[58],"encoder":[59,85],"decoder":[62,117],"with":[63,212],"modified":[65],"ConvNeXt":[66],"v2":[67],"network":[68,155],"backbone,":[71],"connected":[72],"quantizer":[75],"based":[76,157],"on":[77],"residual":[79],"vector":[80],"quantization":[81,150],"(RVQ)":[82],"mechanism.":[83],"compresses":[86],"in":[93,125,179,216],"parallel,":[94,126],"amalgamating":[95],"them":[96],"into":[97],"continuous":[99],"latent":[100],"code":[101,108],"at":[102,206],"reduced":[104],"temporal":[105],"resolution.":[106],"subsequently":[110],"quantized":[111],"quantizer.":[114],"Ultimately,":[115],"reconstructs":[118],"decoded":[129,143,192,221,233],"obtained":[132],"inverse":[134],"short-time":[135],"Fourier":[136],"transform.":[137],"To":[138,166],"ensure":[139],"fidelity":[141],"codecs,":[147,243],"spectral-level":[148],"loss,":[149,151],"generative":[153],"adversarial":[154],"(GAN)":[156],"loss":[158],"are":[159],"collectively":[160],"employed":[161],"for":[162],"training":[163,185],"APCodec.":[165],"support":[167],"low-latency":[168],"streamable":[169],"inference,":[170],"we":[171],"employ":[172],"feed-forward":[173],"layers":[174,178],"causal":[176],"deconvolutional":[177],"incorporating":[181],"knowledge":[183],"distillation":[184],"strategy":[186],"to":[187,241],"enhance":[188],"quality":[190,218,235],"audio.":[193,222],"Experimental":[194],"results":[195],"confirm":[196],"that":[197],"our":[198,227],"proposed":[199,228],"can":[201],"encode":[202],"48":[203],"kHz":[204],"bitrate":[207],"just":[209],"6":[210],"kbps,":[211],"no":[213],"significant":[214],"degradation":[215],"At":[223],"same":[225],"bitrate,":[226],"also":[230],"demonstrates":[231],"superior":[232],"faster":[237],"generation":[238],"speed":[239],"compared":[240],"well-known":[242],"such":[244],"Encodec,":[246],"AudioDec":[247],"DAC.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}