{"id":"https://openalex.org/W7203475474","doi":"https://doi.org/10.48550/arxiv.2608.12951","title":"VoxAudio: Vocalized Audio Synthesis via Multi-Reward Autoregressive Flow Matching","display_name":"VoxAudio: Vocalized Audio Synthesis via Multi-Reward Autoregressive Flow Matching","publication_year":2026,"publication_date":"2026-08-13","ids":{"openalex":"https://openalex.org/W7203475474","doi":"https://doi.org/10.48550/arxiv.2608.12951"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.12951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12951","pdf_url":"https://arxiv.org/pdf/2608.12951","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.12951","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104320351","display_name":"Wenxiang Guo","orcid":"https://orcid.org/0009-0006-7997-4140","observed_orcids":["https://orcid.org/0009-0006-7997-4140"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Wenxiang","raw_affiliation_strings":["Zhejiang University , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University , Hangzhou , China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103228451","display_name":"Changhao Pan","orcid":"https://orcid.org/0009-0004-6023-1764","observed_orcids":["https://orcid.org/0009-0004-6023-1764"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan, Changhao","raw_affiliation_strings":["Zhejiang University , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University , Hangzhou , China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140684530","display_name":"Ziyue Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Ziyue","raw_affiliation_strings":["Zhejiang University , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University , Hangzhou , China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384","observed_orcids":["https://orcid.org/0000-0001-6121-0384","https://orcid.org/0000-0002-6651-1802"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Zhou","raw_affiliation_strings":["Zhejiang University , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University , Hangzhou , China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124888500","display_name":"Fei Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Fei","raw_affiliation_strings":["Zhejiang University , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University , Hangzhou , China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9657999873161316,"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":0.9657999873161316,"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":0.026000000536441803,"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":0.00419999985024333,"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/kv-caching","display_name":"KV caching","score":0.9150000214576721},{"id":"https://openalex.org/keywords/temporal-grounding","display_name":"temporal grounding","score":0.9049999713897705},{"id":"https://openalex.org/keywords/audio-captioning","display_name":"audio captioning","score":0.5040000081062317},{"id":"https://openalex.org/keywords/podcast-production","display_name":"podcast production","score":0.5210000276565552},{"id":"https://openalex.org/keywords/video-dubbing","display_name":"video dubbing","score":0.9300000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808899998664856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6991999745368958},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5550000071525574},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.4975999891757965},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4643000066280365},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.462799996137619},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4544999897480011},{"id":"https://openalex.org/C143273055","wikidata":"https://www.wikidata.org/wiki/Q2382794","display_name":"Delegate","level":2,"score":0.44749999046325684},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.3440999984741211},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3296000063419342},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C161615301","wikidata":"https://www.wikidata.org/wiki/Q309396","display_name":"Keystroke logging","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.12951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12951","pdf_url":"https://arxiv.org/pdf/2608.12951","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.12951","doi":"https://doi.org/10.48550/arxiv.2608.12951","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.12951","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.12951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12951","pdf_url":"https://arxiv.org/pdf/2608.12951","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203475474.pdf","grobid_xml":"https://content.openalex.org/works/W7203475474.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7164854058","https://openalex.org/W7167668725","https://openalex.org/W7202375521","https://openalex.org/W7212824920","https://openalex.org/W4377864887","https://openalex.org/W4416370904","https://openalex.org/W4402111756","https://openalex.org/W7201840745","https://openalex.org/W7133224666","https://openalex.org/W4414696408"],"abstract_inverted_index":{"Vocalized":[0],"audio":[1,7,94,193],"synthesis,":[2],"the":[3,62,82,118,125,144,149,164,195],"task":[4],"of":[5,167,199],"generating":[6],"in":[8],"which":[9,50],"intelligible":[10],"speech":[11,34,55,169],"is":[12],"embedded":[13,168],"within":[14],"an":[15,175],"environmental":[16],"soundscape,":[17],"underpins":[18],"applications":[19],"such":[20],"as":[21],"podcast":[22],"production":[23],"and":[24,57,140,173,190,197,203],"video":[25],"dubbing.":[26],"Existing":[27],"Text-to-Audio":[28],"(T2A)":[29],"systems":[30],"either":[31],"reduce":[32],"quoted":[33],"to":[35,42,108,147],"unintelligible":[36],"vocal":[37,153],"murmur":[38],"or":[39],"delegate":[40],"it":[41,59],"a":[43,67,158,179],"separate":[44],"TTS":[45],"model":[46,72,119],"with":[47,61,88,101,120,170,178],"post-hoc":[48],"mixing,":[49],"forfeits":[51],"control":[52],"over":[53],"when":[54],"occurs":[56],"how":[58],"interacts":[60],"scene.":[63],"We":[64],"present":[65],"VoxAudio,":[66],"causal":[68,86],"autoregressive":[69],"flow":[70],"matching":[71],"that":[73],"addresses":[74],"this":[75],"problem":[76],"from":[77],"three":[78],"complementary":[79],"aspects.":[80],"At":[81,124,143],"architecture":[83],"level,":[84,127,146],"chunk-wise":[85],"factorization":[87],"independent":[89],"per-chunk":[90],"noise":[91],"levels":[92],"lets":[93],"be":[95],"emitted":[96],"through":[97],"sliding-window":[98],"streaming":[99],"inference":[100,110],"KV":[102],"caching":[103],"at":[104,111,207],"variable":[105],"target":[106],"durations;":[107],"enable":[109],"arbitrary":[112],"chunk":[113,122],"granularities,":[114],"we":[115,155],"further":[116],"pretrain":[117],"randomized":[121],"boundaries.":[123],"preference":[126],"multi-reward":[128],"Negative-aware":[129],"FineTuning":[130],"(NFT)":[131],"jointly":[132],"optimizes":[133],"semantic":[134],"fidelity,":[135],"linguistic":[136],"accuracy,":[137],"aesthetic":[138],"quality,":[139],"temporal":[141],"grounding":[142],"data":[145],"supply":[148],"missing":[150],"supervision":[151],"for":[152],"content,":[154],"build":[156],"VoxCorpus,":[157],"large-scale":[159],"corpus":[160],"whose":[161],"captions":[162],"quote":[163],"verbatim":[165],"transcript":[166],"time":[171],"intervals,":[172],"VoxBench,":[174],"interval-annotated":[176],"benchmark":[177],"temporal-grounding":[180],"metric.":[181],"Experiments":[182],"on":[183],"four":[184],"benchmarks":[185],"spanning":[186],"general":[187],"audio,":[188],"speech,":[189],"unified":[191],"vocalized":[192],"validate":[194],"effectiveness":[196],"efficiency":[198],"VoxAudio.":[200],"Our":[201],"code":[202],"demos":[204],"are":[205],"available":[206],"https://voxaudio.github.io.":[208]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-15T00:00:00"}