{"id":"https://openalex.org/W4409355993","doi":"https://doi.org/10.1109/lsp.2025.3560172","title":"A Streamable Neural Audio Codec With Residual Scalar-Vector Quantization for Real-Time Communication","display_name":"A Streamable Neural Audio Codec With Residual Scalar-Vector Quantization for Real-Time Communication","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409355993","doi":"https://doi.org/10.1109/lsp.2025.3560172"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3560172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3560172","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/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/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/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, China"],"raw_orcid":"https://orcid.org/0009-0000-8074-9553","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":2.7073,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.89301345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"1645","last_page":"1649"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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":0.9969000220298767,"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":0.9905999898910522,"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":0.9787999987602234,"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":0.7930306196212769},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6661553978919983},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6543757319450378},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6363537311553955},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5596520304679871},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5145196318626404},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4950970709323883},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.4519958794116974},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.4368240237236023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34268778562545776},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3127155005931854},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2971595525741577},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19305333495140076},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1648571789264679},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.14185509085655212}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7930306196212769},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6661553978919983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6543757319450378},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6363537311553955},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5596520304679871},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5145196318626404},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4950970709323883},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.4519958794116974},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.4368240237236023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34268778562545776},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3127155005931854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2971595525741577},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19305333495140076},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1648571789264679},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.14185509085655212},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3560172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3560172","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"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}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W2067295501","https://openalex.org/W2131738223","https://openalex.org/W2168098717","https://openalex.org/W2972359262","https://openalex.org/W3037038648","https://openalex.org/W3215615641","https://openalex.org/W4297841491","https://openalex.org/W4307323391","https://openalex.org/W4372270198","https://openalex.org/W4381786045","https://openalex.org/W4399875170","https://openalex.org/W4402727900","https://openalex.org/W4406461725","https://openalex.org/W4406496863","https://openalex.org/W6630442970","https://openalex.org/W6675548246","https://openalex.org/W6727697161","https://openalex.org/W6783867762","https://openalex.org/W6848735303","https://openalex.org/W6852581948","https://openalex.org/W6853515095","https://openalex.org/W6857461762","https://openalex.org/W6873477858"],"related_works":["https://openalex.org/W4252424250","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","https://openalex.org/W1999835922"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"StreamCodec,":[3],"a":[4,15,57,74,113,123,132,140,143],"streamable":[5],"neural":[6,101],"audio":[7,48,79,95,102],"codec":[8],"designed":[9],"for":[10,32,46,156],"real-time":[11,36,138,157],"communication.":[12],"StreamCodec":[13,55,92,111],"adopts":[14],"fully":[16],"causal,":[17],"symmetric":[18],"encoder-decoder":[19],"structure":[20],"and":[21,35,44,69,81,130],"operates":[22],"in":[23,73],"the":[24,47,90,106],"modified":[25],"discrete":[26],"cosine":[27],"transform":[28],"(MDCT)":[29],"domain,":[30],"aiming":[31],"low-latency":[33],"inference":[34],"efficient":[37],"generation.":[38],"To":[39],"improve":[40],"codebook":[41],"utilization":[42],"efficiency":[43],"compensate":[45],"quality":[49,96],"loss":[50],"caused":[51],"by":[52],"structural":[53],"causality,":[54],"introduces":[56],"novel":[58],"residual":[59,75],"scalar-vector":[60],"quantizer":[61],"(RSVQ).":[62],"The":[63],"RSVQ":[64],"sequentially":[65],"connects":[66],"scalar":[67],"quantizers":[68,72],"improved":[70],"vector":[71],"manner,":[76],"constructing":[77],"coarse":[78],"contours":[80],"refining":[82],"acoustic":[83],"details,":[84],"respectively.":[85],"Experimental":[86],"results":[87],"confirm":[88],"that":[89],"proposed":[91],"achieves":[93,131],"decoded":[94],"comparable":[97],"to":[98],"advanced":[99],"non-streamable":[100],"codecs.":[103],"Specifically,":[104],"on":[105,139],"16":[107],"kHz":[108],"LibriTTS":[109],"dataset,":[110],"attains":[112],"ViSQOL":[114],"score":[115],"of":[116,126,147],"4.30":[117],"at":[118],"1.5":[119],"kbps.":[120],"It":[121],"has":[122],"fixed":[124],"latency":[125],"only":[127],"20":[128,136],"ms":[129],"generation":[133],"speed":[134],"nearly":[135],"times":[137],"CPU,":[141],"with":[142],"lightweight":[144],"model":[145],"size":[146],"just":[148],"7":[149],"M":[150],"parameters,":[151],"making":[152],"it":[153],"highly":[154],"suitable":[155],"communication":[158],"applications.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}