{"id":"https://openalex.org/W4406461725","doi":"https://doi.org/10.1109/slt61566.2024.10832214","title":"MDCTCodec: A Lightweight MDCT-Based Neural Audio Codec Towards High Sampling Rate and Low Bitrate Scenarios","display_name":"MDCTCodec: A Lightweight MDCT-Based Neural Audio Codec Towards High Sampling Rate and Low Bitrate Scenarios","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461725","doi":"https://doi.org/10.1109/slt61566.2024.10832214"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832214","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":"conference-paper","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/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":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","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":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","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":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. 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":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. 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":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. 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":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. 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":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"540","last_page":"547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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/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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.8866268992424011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7421222925186157},{"id":"https://openalex.org/keywords/constant-bitrate","display_name":"Constant bitrate","score":0.6484445929527283},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.5421953201293945},{"id":"https://openalex.org/keywords/variable-bitrate","display_name":"Variable bitrate","score":0.45291492342948914},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4224320650100708},{"id":"https://openalex.org/keywords/bit-rate","display_name":"Bit rate","score":0.352356493473053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3349180221557617},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.2456187903881073},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18554145097732544},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.14685767889022827},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.10159403085708618},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.10110422968864441}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8866268992424011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421222925186157},{"id":"https://openalex.org/C34339180","wikidata":"https://www.wikidata.org/wiki/Q1325924","display_name":"Constant bitrate","level":4,"score":0.6484445929527283},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.5421953201293945},{"id":"https://openalex.org/C57667952","wikidata":"https://www.wikidata.org/wiki/Q1154443","display_name":"Variable bitrate","level":3,"score":0.45291492342948914},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4224320650100708},{"id":"https://openalex.org/C2987812609","wikidata":"https://www.wikidata.org/wiki/Q194158","display_name":"Bit rate","level":2,"score":0.352356493473053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3349180221557617},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2456187903881073},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18554145097732544},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.14685767889022827},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.10159403085708618},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.10110422968864441},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832214","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":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","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":46,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W1553834069","https://openalex.org/W2020883660","https://openalex.org/W2131738223","https://openalex.org/W2151626637","https://openalex.org/W2168098717","https://openalex.org/W2527729766","https://openalex.org/W2566983320","https://openalex.org/W2899663614","https://openalex.org/W2964073500","https://openalex.org/W2970006822","https://openalex.org/W3037038648","https://openalex.org/W3095095816","https://openalex.org/W3163662330","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/W4379259581","https://openalex.org/W4380551955","https://openalex.org/W4381786045","https://openalex.org/W4386076493","https://openalex.org/W4386384714","https://openalex.org/W4392931276","https://openalex.org/W4399875170","https://openalex.org/W6630442970","https://openalex.org/W6633114069","https://openalex.org/W6727697161","https://openalex.org/W6731445010","https://openalex.org/W6755977528","https://openalex.org/W6757817989","https://openalex.org/W6767111847","https://openalex.org/W6771467084","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6848735303","https://openalex.org/W6852581948","https://openalex.org/W6853165267","https://openalex.org/W6853515095","https://openalex.org/W6855885476"],"related_works":["https://openalex.org/W2097846364","https://openalex.org/W4252424250","https://openalex.org/W2068488051","https://openalex.org/W4252449080","https://openalex.org/W2356163863","https://openalex.org/W2021051713","https://openalex.org/W2462287831","https://openalex.org/W1170819639","https://openalex.org/W2090822070","https://openalex.org/W1987413180"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"MDCTCodec,":[5],"an":[6],"efficient":[7],"lightweight":[8],"end-to-end":[9],"neural":[10],"audio":[11,28,62,107],"codec":[12],"based":[13],"on":[14,144],"the":[15,24,49,52,56,67,80,102,123,145],"modified":[16],"discrete":[17],"cosine":[18],"transform":[19],"(MDCT).":[20],"The":[21],"encoder":[22],"takes":[23],"MDCT":[25,53,84],"spectrum":[26,54,85],"of":[27,129,135,141],"as":[29],"input,":[30],"encoding":[31],"it":[32],"into":[33],"a":[34,43,70,126,132,139],"continuous":[35],"latent":[36,58],"code":[37,59],"which":[38],"is":[39,76],"then":[40],"discretized":[41],"by":[42],"residual":[44],"vector":[45],"quantizer":[46],"(RVQ).":[47],"Subsequently,":[48],"decoder":[50],"decodes":[51],"from":[55],"quantized":[57],"and":[60,99,111,114,138],"reconstructs":[61],"via":[63],"inverse":[64],"MDCT.":[65],"During":[66],"training":[68,110],"phase,":[69],"novel":[71],"multi-resolution":[72],"MDCT-based":[73],"discriminator":[74],"(MR-MDCTD)":[75],"adopted":[77],"to":[78,119],"discriminate":[79],"natural":[81],"or":[82],"decoded":[83,106],"for":[86],"adversarial":[87],"training.":[88],"Experimental":[89],"results":[90],"confirm":[91],"that,":[92],"in":[93],"scenarios":[94],"with":[95],"high":[96,105],"sampling":[97,133],"rates":[98],"low":[100],"bitrates,":[101],"MDCTCodec":[103,124],"exhibited":[104],"quality,":[108],"improved":[109],"generation":[112],"efficiency,":[113],"compact":[115],"model":[116],"size":[117],"compared":[118],"baseline":[120],"codecs.":[121],"Specifically,":[122],"achieved":[125],"ViSQOL":[127],"score":[128],"4.18":[130],"at":[131],"rate":[134],"48":[136],"kHz":[137],"bitrate":[140],"6":[142],"kbps":[143],"public":[146],"VCTK":[147],"corpus.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}