{"id":"https://openalex.org/W4405709614","doi":"https://doi.org/10.1109/iscslp63861.2024.10800013","title":"APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm","display_name":"APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709614","doi":"https://doi.org/10.1109/iscslp63861.2024.10800013"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/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":true,"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"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310848","display_name":"Rui-Chen Zheng","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":"Rui-Chen Zheng","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei","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"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067982618"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.3169,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82045575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"676","last_page":"680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9835000038146973,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9835000038146973,"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":0.9768999814987183,"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/T10860","display_name":"Speech and Audio Processing","score":0.9753000140190125,"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":0.8773378133773804},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.8439356088638306},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.8357083797454834},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7692939043045044},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6091187000274658},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.567011296749115},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5285897254943848},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4968777000904083},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.45745575428009033},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.29929035902023315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24070698022842407},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.2223999798297882},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1963956654071808},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14868885278701782},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11270087957382202},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.057658225297927856}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8773378133773804},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.8439356088638306},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.8357083797454834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692939043045044},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6091187000274658},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.567011296749115},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5285897254943848},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4968777000904083},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.45745575428009033},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.29929035902023315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24070698022842407},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2223999798297882},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1963956654071808},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14868885278701782},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11270087957382202},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.057658225297927856},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-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/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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W2020883660","https://openalex.org/W2130158387","https://openalex.org/W2131738223","https://openalex.org/W2159644785","https://openalex.org/W2168098717","https://openalex.org/W3197273793","https://openalex.org/W3215615641","https://openalex.org/W4307323391","https://openalex.org/W4372260247","https://openalex.org/W4372270198","https://openalex.org/W4381786045","https://openalex.org/W4386076493","https://openalex.org/W4392903006","https://openalex.org/W4399875170","https://openalex.org/W4402672068","https://openalex.org/W4405521053","https://openalex.org/W6630442970","https://openalex.org/W6633114069","https://openalex.org/W6757817989","https://openalex.org/W6783867762","https://openalex.org/W6810129404","https://openalex.org/W6848735303","https://openalex.org/W6852581948","https://openalex.org/W6855375322","https://openalex.org/W6855885476","https://openalex.org/W6857461762"],"related_works":["https://openalex.org/W4252424250","https://openalex.org/W2370747337","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/W3095556352"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,39],"novel":[4],"neural":[5],"audio":[6,21],"codec,":[7],"named":[8],"AP-Codec+,":[9],"which":[10],"is":[11,110],"an":[12,32],"improved":[13],"version":[14],"of":[15,106,116,124],"APCodec.":[16],"The":[17,91,104],"AP-Codec+":[18],"takes":[19],"the":[20,27,47,51,70,74,87,101,113,117,122,125,149],"amplitude":[22],"and":[23,30,55,66,76,81,89,93],"phase":[24],"spectra":[25],"as":[26],"coding":[28],"object,":[29],"employs":[31],"adversarial":[33,67],"training":[34,42,49,72,84,109,152],"strategy.":[35],"Innovatively,":[36],"we":[37],"propose":[38],"two-stage":[40],"joint-individual":[41],"paradigm":[43],"for":[44,86],"APCodec+.":[45],"In":[46,69],"joint":[48],"stage,":[50,73],"encoder,":[52],"quantizer,":[53],"decoder":[54,88,92],"discriminator":[56,94],"are":[57,95],"jointly":[58],"trained":[59,97],"with":[60,141],"complete":[61],"spectral":[62],"loss,":[63,65],"quantization":[64,102],"loss.":[68,103],"individual":[71,108],"encoder":[75],"quantizer":[77],"fix":[78],"their":[79],"parameters":[80],"provide":[82],"high-quality":[83],"data":[85],"discriminator.":[90],"individually":[96],"from":[98],"scratch":[99],"without":[100],"purpose":[105],"introducing":[107],"to":[111,148],"reduce":[112],"learning":[114],"difficulty":[115],"decoder,":[118],"thereby":[119],"further":[120],"improving":[121],"fidelity":[123],"decoded":[126],"audio.":[127],"Experimental":[128],"results":[129],"confirm":[130],"that":[131],"our":[132],"proposed":[133,150],"APCodec+":[134],"at":[135,144],"low":[136],"bitrates":[137],"achieves":[138],"comparable":[139],"performance":[140],"baseline":[142],"codecs":[143],"higher":[145],"bitrates,":[146],"thanks":[147],"staged":[151],"paradigm.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
