{"id":"https://openalex.org/W4406461300","doi":"https://doi.org/10.1109/slt61566.2024.10832324","title":"NDVQ: Robust Neural Audio Codec With Normal Distribution-Based Vector Quantization","display_name":"NDVQ: Robust Neural Audio Codec With Normal Distribution-Based Vector Quantization","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461300","doi":"https://doi.org/10.1109/slt61566.2024.10832324"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832324","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":"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/A5108896784","display_name":"Zhikang Niu","orcid":"https://orcid.org/0009-0002-2709-9381"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhikang Niu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079533447","display_name":"Sanyuan Chen","orcid":"https://orcid.org/0000-0002-3082-6052"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanyuan Chen","raw_affiliation_strings":["Microsoft Research Asia,China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106557565","display_name":"Long Zhou","orcid":"https://orcid.org/0009-0006-1919-4943"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Zhou","raw_affiliation_strings":["Microsoft Research Asia,China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438492","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-0623-9114"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102771326","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034770439","display_name":"Shujie Liu","orcid":"https://orcid.org/0000-0003-0012-5199"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Research Asia,China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5108896784"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.7332,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72632135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"705","last_page":"710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"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":0.8089220523834229},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.7709725499153137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7229987978935242},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5994042754173279},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5202318429946899},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4783579707145691},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46419915556907654},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.4484265148639679},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33808356523513794},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3347136676311493},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24482184648513794},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.15233665704727173},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10437121987342834}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8089220523834229},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.7709725499153137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229987978935242},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5994042754173279},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5202318429946899},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4783579707145691},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46419915556907654},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.4484265148639679},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33808356523513794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3347136676311493},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24482184648513794},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.15233665704727173},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10437121987342834}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832324","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":[{"id":"https://metadata.un.org/sdg/7","score":0.4099999964237213,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W1552314771","https://openalex.org/W1670669358","https://openalex.org/W1728888090","https://openalex.org/W2020883660","https://openalex.org/W2107860279","https://openalex.org/W2119125873","https://openalex.org/W2527729766","https://openalex.org/W2752796333","https://openalex.org/W2963242190","https://openalex.org/W2964058413","https://openalex.org/W2972359262","https://openalex.org/W3095095816","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4205788663","https://openalex.org/W4307323391","https://openalex.org/W4311415873","https://openalex.org/W4313679638","https://openalex.org/W6727697161","https://openalex.org/W6779823529","https://openalex.org/W6848735303","https://openalex.org/W6853515095"],"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":{"Built":[0],"upon":[1],"vector":[2],"quantization":[3],"(VQ),":[4],"discrete":[5],"audio":[6,14,18,157,166],"codec":[7,131],"models":[8,22],"have":[9],"achieved":[10],"great":[11],"success":[12],"in":[13,26,35,40,163,172],"compression":[15,158],"and":[16,29,102,125,148,168],"autoregressive":[17],"generation.":[19],"However,":[20],"existing":[21,156],"face":[23],"substantial":[24],"challenges":[25,53],"perceptual":[27],"quality":[28,167],"signal":[30],"distortion,":[31],"especially":[32],"when":[33],"operating":[34],"extremely":[36],"low":[37,174],"bandwidth,":[38],"rooted":[39],"the":[41,44,84,96,107,136],"sensitivity":[42],"of":[43,165],"VQ":[45,71,85,130],"codebook":[46,114],"to":[47,98],"noise.":[48],"This":[49],"degradation":[50],"poses":[51],"significant":[52],"for":[54],"several":[55],"downstream":[56],"tasks,":[57],"such":[58,160],"as":[59,161],"codec-based":[60],"speech":[61],"synthesis.":[62],"To":[63],"address":[64],"this":[65],"issue,":[66],"we":[67],"propose":[68],"a":[69,89,99,117,133],"novel":[70],"method,":[72],"Normal":[73],"Distribution-based":[74],"Vector":[75],"Quantization":[76],"(NDVQ),":[77],"by":[78,105,122],"introducing":[79],"an":[80],"explicit":[81],"margin":[82],"between":[83],"codes":[86],"via":[87],"learning":[88],"variance.":[90,126],"Specifically,":[91],"our":[92],"approach":[93],"involves":[94],"mapping":[95],"waveform":[97],"latent":[100],"space":[101],"quantizing":[103],"it":[104],"selecting":[106],"most":[108],"likely":[109],"normal":[110,119],"distribution,":[111],"with":[112,142],"each":[113],"entry":[115],"representing":[116],"unique":[118],"distribution":[120],"defined":[121],"its":[123],"mean":[124],"Using":[127],"these":[128],"distribution-based":[129],"codes,":[132],"decoder":[134],"reconstructs":[135],"input":[137],"waveform.":[138],"NDVQ":[139,154],"is":[140],"trained":[141],"additional":[143],"distribution-related":[144],"losses,":[145],"alongside":[146],"reconstruction":[147],"discrimination":[149],"losses.":[150],"Experiments":[151],"demonstrate":[152],"that":[153],"outperforms":[155],"baselines,":[159],"EnCodec,":[162],"terms":[164],"zero-shot":[169],"TTS,":[170],"particularly":[171],"very":[173],"bandwidth":[175],"scenarios.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}