{"id":"https://openalex.org/W4412944968","doi":"https://doi.org/10.18653/v1/2025.acl-long.912","title":"LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","display_name":"LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944968","doi":"https://doi.org/10.18653/v1/2025.acl-long.912"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.912","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.912","pdf_url":"https://aclanthology.org/2025.acl-long.912.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.912.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078940234","display_name":"Qingkai Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingkai Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060210788","display_name":"Zhou Yan","orcid":"https://orcid.org/0000-0003-4998-2490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045398529","display_name":"Shoutao Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shoutao Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031466943","display_name":"Shaolei Zhang","orcid":"https://orcid.org/0000-0002-7254-9380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaolei Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101398253","display_name":"Yang Feng","orcid":"https://orcid.org/0000-0001-7362-9844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Feng","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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18617","last_page":"18629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9835000038146973,"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/T12031","display_name":"Speech and dialogue systems","score":0.9835000038146973,"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/T12128","display_name":"AI in Service Interactions","score":0.9771000146865845,"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/T10028","display_name":"Topic Modeling","score":0.9557999968528748,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/chatbot","display_name":"Chatbot","score":0.925618588924408},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.751812219619751},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.705780029296875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5626379251480103},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46418824791908264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4083670973777771},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05719438195228577},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05635592341423035}],"concepts":[{"id":"https://openalex.org/C2779041454","wikidata":"https://www.wikidata.org/wiki/Q870780","display_name":"Chatbot","level":2,"score":0.925618588924408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751812219619751},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.705780029296875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5626379251480103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46418824791908264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4083670973777771},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05719438195228577},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05635592341423035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.912","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.912","pdf_url":"https://aclanthology.org/2025.acl-long.912.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.912","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.912","pdf_url":"https://aclanthology.org/2025.acl-long.912.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944968.pdf","grobid_xml":"https://content.openalex.org/works/W4412944968.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4383501580","https://openalex.org/W4214931137","https://openalex.org/W4313813117","https://openalex.org/W4382052417","https://openalex.org/W3192088754","https://openalex.org/W4387007686","https://openalex.org/W3084631705","https://openalex.org/W3176146353","https://openalex.org/W4293646425","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Real-time,":[0],"intelligent,":[1],"and":[2,69,94],"natural":[3],"speech":[4,40,55,67,73,81,95,113],"interaction":[5],"is":[6,58],"an":[7,70],"essential":[8],"part":[9],"of":[10,20,39,51,110,112],"the":[11,18,61],"next-generation":[12],"human-computer":[13],"interaction.Recent":[14],"advancements":[15],"have":[16],"showcased":[17],"potential":[19],"building":[21],"intelligent":[22],"spoken":[23,91],"chatbots":[24],"based":[25],"on":[26,77,89,108],"large":[27],"language":[28,41],"models":[29,42],"(LLMs).In":[30],"this":[31],"paper,":[32],"we":[33],"introduce":[34],"LLaMA-Omni":[35,84],"2,":[36],"a":[37,66],"series":[38,63],"(SpeechLMs)":[43],"ranging":[44],"from":[45],"0.5B":[46],"to":[47],"14B":[48],"parameters,":[49],"capable":[50],"achieving":[52],"highquality":[53],"real-time":[54],"interaction.LLaMA-Omni":[56],"2":[57,85],"built":[59],"upon":[60],"Qwen2.5":[62],"models,":[64],"integrating":[65],"encoder":[68],"autoregressive":[71],"streaming":[72],"decoder.Despite":[74],"being":[75],"trained":[76,107],"only":[78],"200K":[79],"multi-turn":[80],"dialogue":[82],"samples,":[83],"demonstrates":[86],"strong":[87],"performance":[88],"several":[90],"question":[92],"answering":[93],"instruction":[96],"following":[97],"benchmarks,":[98],"surpassing":[99],"previous":[100],"state-of-theart":[101],"SpeechLMs":[102],"like":[103],"GLM-4-Voice,":[104],"which":[105],"was":[106],"millions":[109],"hours":[111],"data.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}