{"id":"https://openalex.org/W7225328658","doi":"https://doi.org/10.48550/arxiv.2611.06043","title":"Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription","display_name":"Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription","publication_year":2026,"publication_date":"2026-11-04","ids":{"openalex":"https://openalex.org/W7225328658","doi":"https://doi.org/10.48550/arxiv.2611.06043"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.06043","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.06043","pdf_url":"https://arxiv.org/pdf/2611.06043","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.06043","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160771104","display_name":"Daniel Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Daniel","raw_affiliation_strings":["NetEase Youdao , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Youdao , Beijing , China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160772001","display_name":"Qi He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He, Qi","raw_affiliation_strings":["NetEase Youdao , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Youdao , Beijing , China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114092590","display_name":"Shaoxiong Duan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duan, Shaoxiong","raw_affiliation_strings":["NetEase Youdao , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Youdao , Beijing , China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160742804","display_name":"Yingjie Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yingjie","raw_affiliation_strings":["NetEase Youdao , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Youdao , Beijing , China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006296087","display_name":"Qiao Cheng","orcid":"https://orcid.org/0009-0004-8598-8341","observed_orcids":["https://orcid.org/0009-0004-8598-8341"]},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng, Qiao","raw_affiliation_strings":["NetEase Youdao , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Youdao , Beijing , China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160848039","display_name":"Yitao Duan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duan, Yitao","raw_affiliation_strings":["NetEase Youdao , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Youdao , Beijing , China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"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":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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":0.0,"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/streaming-speech-recognition","display_name":"streaming speech recognition","score":0.9539999961853027},{"id":"https://openalex.org/keywords/real-time-transcription","display_name":"real-time transcription","score":0.8700000047683716},{"id":"https://openalex.org/keywords/post-training-adaptation","display_name":"post-training adaptation","score":0.6890000104904175},{"id":"https://openalex.org/keywords/chinese-speech-recognition","display_name":"Chinese speech recognition","score":0.6290000081062317},{"id":"https://openalex.org/keywords/english-speech-recognition","display_name":"English speech recognition","score":0.9369999766349792},{"id":"https://openalex.org/keywords/low-latency","display_name":"low latency","score":0.4620000123977661},{"id":"https://openalex.org/keywords/monotonicity","display_name":"monotonicity","score":0.4650000035762787}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8792999982833862},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.814300000667572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7046999931335449},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5738000273704529},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2535000145435333},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.06043","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.06043","pdf_url":"https://arxiv.org/pdf/2611.06043","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.2611.06043","doi":"https://doi.org/10.48550/arxiv.2611.06043","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.06043","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:2611.06043","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.06043","pdf_url":"https://arxiv.org/pdf/2611.06043","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/W7225328658.pdf","grobid_xml":"https://content.openalex.org/works/W7225328658.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2125336414","https://openalex.org/W2394671344","https://openalex.org/W2773781902","https://openalex.org/W2799473636","https://openalex.org/W2887005286","https://openalex.org/W2981857663","https://openalex.org/W2992229580","https://openalex.org/W2998814410","https://openalex.org/W3095410713","https://openalex.org/W3095503786","https://openalex.org/W3095950464","https://openalex.org/W3095996511","https://openalex.org/W3111562797","https://openalex.org/W3119308075","https://openalex.org/W3128478537","https://openalex.org/W3170405627","https://openalex.org/W3198694222","https://openalex.org/W3203407300","https://openalex.org/W4221146809","https://openalex.org/W4285271575","https://openalex.org/W4319166707","https://openalex.org/W4319862635","https://openalex.org/W4319862688","https://openalex.org/W4386576722","https://openalex.org/W4391631327","https://openalex.org/W4392669897","https://openalex.org/W4392903330","https://openalex.org/W4399758690","https://openalex.org/W4402112520","https://openalex.org/W4408345835","https://openalex.org/W4408353174","https://openalex.org/W4409362822","https://openalex.org/W4412886767","https://openalex.org/W4415433948","https://openalex.org/W6959925547","https://openalex.org/W7076811890","https://openalex.org/W7126278909","https://openalex.org/W7128773640","https://openalex.org/W7155058474","https://openalex.org/W7212018612","https://openalex.org/W7220708362"],"related_works":["https://openalex.org/W7212059113","https://openalex.org/W7213242585","https://openalex.org/W7076811890","https://openalex.org/W7128773640","https://openalex.org/W7125200645","https://openalex.org/W3196427171","https://openalex.org/W3092122846","https://openalex.org/W7212018612","https://openalex.org/W7155203048","https://openalex.org/W3093346109"],"abstract_inverted_index":{"Streaming":[0],"speech":[1],"recognition":[2,156],"is":[3,25,65,88,111],"increasingly":[4],"consumed":[5],"by":[6,67],"machines,":[7],"such":[8],"as":[9,19],"translators":[10],"and":[11,61,75,84,122,194,198],"voice":[12],"agents,":[13],"that":[14,24,51,101,109,126,152],"act":[15],"on":[16,70,90],"each":[17],"token":[18,23],"it":[20],"appears.":[21],"A":[22],"later":[26],"revised":[27],"costs":[28],"wasted":[29],"work":[30],"or":[31],"a":[32,46,98,128,137,141,180],"wrong":[33],"action.":[34],"In":[35],"this":[36,105],"work,":[37],"we":[38,102],"present":[39],"Confucius4-R2T2":[40],"(short":[41],"for":[42],"Real":[43],"Real-Time":[44],"Transcription),":[45],"stable-prefix":[47,142],"streaming":[48,143,155],"ASR":[49,185],"model":[50,139,192],"never":[52],"modifies":[53],"its":[54,80],"earlier":[55,130],"output":[56],"while":[57,78,164],"maintaining":[58],"high":[59],"accuracy":[60],"low":[62,169],"latency.":[63],"R2T2":[64,153],"obtained":[66],"post-training":[68,177],"Qwen3-ASR-1.7B":[69],"1,500":[71],"hours":[72],"of":[73,93],"Chinese":[74],"English":[76],"audio":[77,82],"freezing":[79],"pre-trained":[81],"encoder":[83],"projector.":[85],"The":[86],"adaptation":[87],"based":[89],"the":[91,114,119,159,176,191],"concept":[92],"Longest":[94],"Stable":[95],"Prefix":[96],"(LSP),":[97],"new":[99],"notion":[100],"introduce":[103],"in":[104],"work.":[106],"We":[107,189],"prove":[108],"LSP":[110,134],"monotone":[112],"under":[113],"prefix":[115],"order,":[116],"consistent":[117],"with":[118,168],"full-audio":[120],"output,":[121],"maximal":[123],"among":[124],"labels":[125,135],"equal":[127],"whole":[129],"output.":[131],"Learning":[132],"from":[133,183],"converts":[136],"full-context":[138,162,184],"into":[140],"one":[144],"without":[145],"any":[146],"architectural":[147],"change.":[148],"Extensive":[149],"evaluations":[150],"show":[151],"brings":[154],"close":[157],"to":[158,186],"base":[160],"model's":[161],"quality":[163],"delivering":[165],"stable":[166,187],"text":[167],"emission":[170],"lag.":[171],"Its":[172],"gains":[173],"extend":[174],"beyond":[175],"languages,":[178],"demonstrating":[179],"practical":[181],"path":[182],"streaming.":[188],"open-source":[190],"weights":[193],"code":[195],"at":[196],"https://huggingface.co/netease-youdao/Confucius4-R2T2":[197],"https://github.com/netease-youdao/Confucius4-R2T2.":[199]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-06T00:00:00"}