{"id":"https://openalex.org/W7135068979","doi":"https://doi.org/10.48550/arxiv.2603.10420","title":"FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System","display_name":"FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135068979","doi":"https://doi.org/10.48550/arxiv.2603.10420"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.10420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.10420","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119818609","display_name":"Kaituo Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Kaituo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128880408","display_name":"Yan Jia","orcid":null},"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/A5128815379","display_name":"Kai Huang","orcid":null},"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/A5128867754","display_name":"Junjie Chen","orcid":null},"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/A5128814849","display_name":"Wenpeng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Wenpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128918371","display_name":"Kun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101692260","display_name":"Fenglong Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Feng-Long","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128854015","display_name":"Xu Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128883349","display_name":"Yao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yao","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":false,"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":0.9118000268936157,"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":0.9118000268936157,"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/T10863","display_name":"Voice and Speech Disorders","score":0.03310000151395798,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.016599999740719795,"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/punctuation","display_name":"Punctuation","score":0.664900004863739},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6349999904632568},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.46399998664855957},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.41679999232292175},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39309999346733093},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.3928000032901764},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38909998536109924},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.38199999928474426},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3610000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8033999800682068},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7278000116348267},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.664900004863739},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6349999904632568},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4442000091075897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4424000084400177},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.41679999232292175},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3610000014305115},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3264999985694885},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.10420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.10420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4382683038711548,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"FireRedASR2S,":[2],"a":[3,17],"state-of-the-art":[4],"industrial-grade":[5],"all-in-one":[6],"automatic":[7],"speech":[8,57,206],"recognition":[9,76],"(ASR)":[10],"system.":[11],"It":[12],"integrates":[13],"four":[14],"modules":[15,34],"in":[16,205],"unified":[18],"pipeline:":[19],"ASR,":[20],"Voice":[21],"Activity":[22],"Detection":[23],"(VAD),":[24],"Spoken":[25],"Language":[26],"Identification":[27],"(LID),":[28],"and":[29,52,58,65,68,78,81,94,101,110,132,145,152,162,166,179,189,212],"Punctuation":[30],"Prediction":[31],"(Punc).":[32],"All":[33],"achieve":[35],"SOTA":[36],"performance":[37],"on":[38,89,96,119],"the":[39,120,137],"evaluated":[40],"benchmarks:":[41],"FireRedASR2:":[42],"An":[43,113,155],"ASR":[44],"module":[45,115,158,186],"with":[46],"two":[47],"variants,":[48],"FireRedASR2-LLM":[49,84],"(8B+":[50],"parameters)":[51,117],"FireRedASR2-AED":[53],"(1B+":[54],"parameters),":[55],"supporting":[56,127,159],"singing":[59],"transcription":[60],"for":[61,187],"Mandarin,":[62],"Chinese":[63,99,164,188],"dialects":[64,100,165],"accents,":[66],"English,":[67],"code-switching.":[69],"Compared":[70],"to":[71],"FireRedASR,":[72],"FireRedASR2":[73],"delivers":[74],"improved":[75],"accuracy":[77],"broader":[79],"dialect":[80],"accent":[82],"coverage.":[83],"achieves":[85,141,173,195],"2.89%":[86],"average":[87,197],"CER":[88],"4":[90],"public":[91,98],"Mandarin":[92],"benchmarks":[93],"11.55%":[95],"19":[97],"accents":[102],"benchmarks,":[103,193],"outperforming":[104,148,177,199],"competitive":[105],"baselines":[106],"including":[107],"Doubao-ASR,":[108],"Qwen3-ASR,":[109],"Fun-ASR.":[111],"FireRedVAD:":[112],"ultra-lightweight":[114],"(0.6M":[116],"based":[118],"Deep":[121],"Feedforward":[122],"Sequential":[123],"Memory":[124],"Network":[125],"(DFSMN),":[126],"streaming":[128],"VAD,":[129,131],"non-streaming":[130],"multi-label":[133],"VAD":[134],"(mVAD).":[135],"On":[136,168,191],"FLEURS-VAD-102":[138],"benchmark,":[139],"it":[140,172,194],"97.57%":[142],"frame-level":[143],"F1":[144],"99.60%":[146],"AUC-ROC,":[147],"Silero-VAD,":[149],"TEN-VAD,":[150],"FunASR-VAD,":[151],"WebRTC-VAD.":[153],"FireRedLID:":[154],"Encoder-Decoder":[156],"LID":[157],"100+":[160],"languages":[161],"20+":[163],"accents.":[167],"FLEURS":[169],"(82":[170],"languages),":[171],"97.18%":[174],"utterance-level":[175],"accuracy,":[176],"Whisper":[178],"SpeechBrain.":[180],"FireRedPunc:":[181],"A":[182],"BERT-style":[183],"punctuation":[184],"prediction":[185],"English.":[190],"multi-domain":[192],"78.90%":[196],"F1,":[198],"FunASR-Punc":[200],"(62.77%).":[201],"To":[202],"advance":[203],"research":[204],"processing,":[207],"we":[208],"release":[209],"model":[210],"weights":[211],"code":[213],"at":[214],"https://github.com/FireRedTeam/FireRedASR2S.":[215]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-13T00:00:00"}