{"id":"https://openalex.org/W4414849600","doi":"https://doi.org/10.48550/arxiv.2502.17239","title":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction","display_name":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction","publication_year":2025,"publication_date":"2025-02-24","ids":{"openalex":"https://openalex.org/W4414849600","doi":"https://doi.org/10.48550/arxiv.2502.17239"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.17239","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.17239","pdf_url":"https://arxiv.org/pdf/2502.17239","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":"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/2502.17239","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054795082","display_name":"Tianpeng Li","orcid":"https://orcid.org/0000-0002-6665-1151","observed_orcids":["https://orcid.org/0000-0002-6665-1151"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Tianpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361819","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-2827-0630","observed_orcids":["https://orcid.org/0000-0002-2827-0630"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375823","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-6272-4069","observed_orcids":["https://orcid.org/0000-0002-6272-4069"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053328795","display_name":"Yuanbo Fang","orcid":"https://orcid.org/0000-0002-3830-0178","observed_orcids":["https://orcid.org/0000-0002-3830-0178"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Yuanbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008372111","display_name":"Da Pan","orcid":"https://orcid.org/0009-0000-4934-4347","observed_orcids":["https://orcid.org/0009-0000-4934-4347"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Da","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Mingrui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Mingrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767139","display_name":"Zheng Liang","orcid":"https://orcid.org/0000-0001-6473-8512","observed_orcids":["https://orcid.org/0000-0001-6473-8512"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009600744","display_name":"Zehuan Li","orcid":"https://orcid.org/0000-0001-8084-7428","observed_orcids":["https://orcid.org/0000-0001-8084-7428"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zehuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045304707","display_name":"Mingan Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Mingan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112223588","display_name":"Guosheng Dong","orcid":"https://orcid.org/0009-0006-2955-9272","observed_orcids":["https://orcid.org/0009-0006-2955-9272"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Guosheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699455","display_name":"Jianhua Xu","orcid":"https://orcid.org/0000-0001-6134-4833","observed_orcids":["https://orcid.org/0000-0001-6134-4833","https://orcid.org/0000-0002-7852-2517"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jianhua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102777251","display_name":"Haoze Sun","orcid":"https://orcid.org/0000-0002-7037-701X","observed_orcids":["https://orcid.org/0000-0002-7037-701X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Haoze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080612265","display_name":"Zenan Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zenan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056336684","display_name":"Weipeng Chen","orcid":"https://orcid.org/0000-0001-9293-7578","observed_orcids":["https://orcid.org/0000-0001-9293-7578","https://orcid.org/0000-0001-6396-9300"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Weipeng","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":2,"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":0.9911999702453613,"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":0.9911999702453613,"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/T12031","display_name":"Speech and dialogue systems","score":0.005900000222027302,"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":0.002300000051036477,"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/large-audio-language-models","display_name":"large audio language models","score":0.8050000071525574},{"id":"https://openalex.org/keywords/question-answering","display_name":"question answering","score":0.8289999961853027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185999989509583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6085000038146973},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5565999746322632},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4194999933242798},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.39640000462532043},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39100000262260437},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.3637000024318695},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.34860000014305115},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.33820000290870667},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3370000123977661},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.2581000030040741},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.17239","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.17239","pdf_url":"https://arxiv.org/pdf/2502.17239","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.17239","doi":"https://doi.org/10.48550/arxiv.2502.17239","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.17239","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.17239","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.17239","pdf_url":"https://arxiv.org/pdf/2502.17239","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417137030","https://openalex.org/W7117257722","https://openalex.org/W4403556012","https://openalex.org/W4388684946","https://openalex.org/W7160911711","https://openalex.org/W7127889711","https://openalex.org/W4407758949","https://openalex.org/W4378510408","https://openalex.org/W4414903259","https://openalex.org/W4415253992"],"abstract_inverted_index":{"We":[0],"introduce":[1],"Baichuan-Audio,":[2],"an":[3,70],"end-to-end":[4],"audio":[5,12,72,78,113],"large":[6],"language":[7,109],"model":[8,118,136,151],"that":[9,57,107],"seamlessly":[10],"integrates":[11],"understanding":[13,110],"and":[14,31,63,93,124,132,144,152],"generation.":[15],"It":[16],"features":[17],"a":[18,36,47,103],"text-guided":[19],"aligned":[20],"speech":[21,26,45,58],"generation":[22,32],"mechanism,":[23],"enabling":[24],"real-time":[25,121,141],"interaction":[27],"with":[28],"both":[29,61],"comprehension":[30],"capabilities.":[33],"Baichuan-Audio":[34],"leverages":[35],"pre-trained":[37],"ASR":[38],"model,":[39],"followed":[40],"by":[41],"multi-codebook":[42,54],"discretization":[43],"of":[44,50,89,98],"at":[46,157],"frame":[48],"rate":[49],"12.5":[51],"Hz.":[52],"This":[53],"setup":[55],"ensures":[56],"tokens":[59],"retain":[60],"semantic":[62],"acoustic":[64],"information.":[65],"To":[66,85],"further":[67],"enhance":[68],"modeling,":[69],"independent":[71],"head":[73],"is":[74],"employed":[75],"to":[76],"process":[77],"tokens,":[79],"effectively":[80],"capturing":[81],"their":[82],"unique":[83],"characteristics.":[84],"mitigate":[86],"the":[87,95,99,117],"loss":[88],"intelligence":[90],"during":[91],"pre-training":[92,105],"preserve":[94],"original":[96],"capabilities":[97],"LLM,":[100],"we":[101],"propose":[102],"two-stage":[104],"strategy":[106],"maintains":[108],"while":[111],"enhancing":[112],"modeling.":[114],"Following":[115],"alignment,":[116],"excels":[119],"in":[120,140],"speech-based":[122],"conversation":[123],"exhibits":[125,145],"outstanding":[126],"question-answering":[127,147],"capabilities,":[128],"demonstrating":[129],"its":[130],"versatility":[131],"efficiency.":[133],"The":[134],"proposed":[135],"demonstrates":[137],"superior":[138],"performance":[139],"spoken":[142],"dialogue":[143],"strong":[146],"abilities.":[148],"Our":[149],"code,":[150],"training":[153],"data":[154],"are":[155],"available":[156],"https://github.com/baichuan-inc/Baichuan-Audio":[158]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}