{"id":"https://openalex.org/W7204239488","doi":"https://doi.org/10.48550/arxiv.2608.24168","title":"FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation","display_name":"FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204239488","doi":"https://doi.org/10.48550/arxiv.2608.24168"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.24168","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24168","pdf_url":"https://arxiv.org/pdf/2608.24168","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/2608.24168","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069616800","display_name":"Feiyu Shen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Feiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119818608","display_name":"Fenglong Xie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Fenglong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147598426","display_name":"Junjie Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148502479","display_name":"Kun Xie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139136587","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-9051-2111","observed_orcids":["https://orcid.org/0000-0001-9051-2111"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146687854","display_name":"Xu Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102662617","display_name":"Xuelong Geng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geng, Xuelong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128880408","display_name":"Yan Jia","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148289246","display_name":"Kai Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147483297","display_name":"Yichen Han","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Yichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148201435","display_name":"Yixuan Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147578373","display_name":"Ziqi Dai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Ziqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133277777","display_name":"Junjie Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123896749","display_name":"Kai Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119818607","display_name":"Manzhen Wei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Manzhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5148214450","display_name":"Yao Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.9980000257492065,"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":0.9980000257492065,"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/T10860","display_name":"Speech and Audio Processing","score":0.0010999999940395355,"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":0.000699999975040555,"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/audio-understanding","display_name":"audio understanding","score":0.7369999885559082},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"speech synthesis","score":0.8560000061988831},{"id":"https://openalex.org/keywords/speech-editing","display_name":"speech editing","score":0.9049999713897705},{"id":"https://openalex.org/keywords/audio-encoder","display_name":"audio encoder","score":0.6019999980926514},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.6209999918937683},{"id":"https://openalex.org/keywords/diffusion-transformer","display_name":"diffusion transformer","score":0.4059999883174896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7680000066757202},{"id":"https://openalex.org/keywords/long-context-modeling","display_name":"long-context modeling","score":0.6169999837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008000254631042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6378999948501587},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5720999836921692},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.560699999332428},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.38190001249313354},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37610000371932983},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31450000405311584},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C2778488704","wikidata":"https://www.wikidata.org/wiki/Q15190726","display_name":"Audio equipment","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24168","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24168","pdf_url":"https://arxiv.org/pdf/2608.24168","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.24168","doi":"https://doi.org/10.48550/arxiv.2608.24168","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24168","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:2608.24168","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24168","pdf_url":"https://arxiv.org/pdf/2608.24168","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/W7204239488.pdf","grobid_xml":"https://content.openalex.org/works/W7204239488.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7203779947","https://openalex.org/W7127889711","https://openalex.org/W4416156439","https://openalex.org/W4381786045","https://openalex.org/W7117988839","https://openalex.org/W4391591726","https://openalex.org/W4399554908","https://openalex.org/W6929354950","https://openalex.org/W7163055123","https://openalex.org/W6912974643"],"abstract_inverted_index":{"A":[0,19],"unified":[1,68],"audio":[2,48,132,163,178,222],"model":[3,50,70,230],"must":[4],"recognize":[5],"and":[6,10,17,79,131,152,154,180,186,198,206,224],"understand":[7],"linguistic,":[8],"paralinguistic,":[9],"environmental":[11],"information":[12],"while":[13,100],"supporting":[14],"speech":[15,33,101,156,208,226],"synthesis":[16],"editing.":[18,157,209],"key":[20],"challenge":[21],"is":[22,63,93,236],"representation:":[23],"understanding":[24,78,179,223],"favors":[25],"compact":[26],"features":[27,37],"suited":[28],"to":[29,71,88,119,138,142],"long-context":[30],"modeling,":[31],"whereas":[32],"generation":[34,80,104,227],"requires":[35],"reconstructible":[36],"that":[38],"preserve":[39],"fine-grained":[40],"acoustic":[41,122,155,207],"detail.":[42],"We":[43],"introduce":[44],"FireRedAudio,":[45],"a":[46,52,82,96,106,116,229],"general-purpose":[47],"language":[49],"with":[51,134],"shared":[53],"9B-parameter":[54],"LLM.":[55,86],"To":[56],"the":[57,64,135,213],"best":[58],"of":[59,140,161,215,231],"our":[60],"knowledge,":[61],"it":[62],"first":[65],"publicly":[66],"disclosed":[67],"audio-language":[69],"provide":[72],"separate":[73],"continuous":[74,121,217],"input":[75,218],"representations":[76,219],"for":[77,103,220],"within":[81],"single":[83],"trainable":[84],"autoregressive":[85],"Audio":[87,98],"be":[89],"recognized":[90],"or":[91,114,174],"analyzed":[92],"processed":[94],"by":[95],"dedicated":[97],"Encoder,":[99],"inputs":[102],"use":[105],"RedAE-based":[107],"pathway.":[108],"The":[109],"LLM":[110],"directly":[111],"generates":[112],"text":[113],"conditions":[115],"flow-matching":[117],"DiT":[118],"produce":[120],"latents.":[123],"Through":[124],"progressive":[125],"multitask":[126],"training,":[127],"FireRedAudio":[128,171],"supports":[129],"ASR":[130],"understanding,":[133],"latter":[136],"extending":[137],"recordings":[139],"up":[141],"one":[143],"hour,":[144],"as":[145,147],"well":[146],"zero-shot":[148,190],"TTS,":[149,151,191,197],"Instruct":[150,196],"semantic":[153,205],"Its":[158],"structured":[159],"organization":[160],"long-form":[162],"achieves":[164,172],"second-level":[165],"timestamp":[166],"accuracy.":[167],"Across":[168],"comprehensive":[169],"evaluations,":[170],"competitive":[173],"leading":[175,192],"performance":[176],"in":[177,189,195,203,228],"multilingual":[181],"ASR,":[182],"strong":[183],"content":[184],"accuracy":[185],"speaker":[187],"preservation":[188],"instruction":[193],"following":[194],"substantial":[199],"improvements":[200],"over":[201],"Ming-UniAudio-Edit":[202],"both":[204],"These":[210],"results":[211],"demonstrate":[212],"viability":[214],"decoupled":[216],"unifying":[221],"continuous-latent":[225],"moderate":[232],"scale.":[233],"Our":[234],"code":[235],"available":[237],"at":[238],"https://github.com/FireRedTeam/FireRedAudio.":[239]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-27T00:00:00"}