{"id":"https://openalex.org/W4391591726","doi":"https://doi.org/10.48550/arxiv.2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","display_name":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","publication_year":2024,"publication_date":"2024-02-02","ids":{"openalex":"https://openalex.org/W4391591726","doi":"https://doi.org/10.48550/arxiv.2402.01831"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2402.01831","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.01831","pdf_url":"https://arxiv.org/pdf/2402.01831","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":"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/2402.01831","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042062740","display_name":"Zhifeng Kong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kong, Zhifeng","raw_affiliation_strings":["NVIDIA , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031240854","display_name":"Arushi Goel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Goel, Arushi","raw_affiliation_strings":["NVIDIA , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058296176","display_name":"Rohan Badlani","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Badlani, Rohan","raw_affiliation_strings":["NVIDIA , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ping, Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping, Wei","raw_affiliation_strings":["NVIDIA , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Valle, Rafael","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valle, Rafael","raw_affiliation_strings":["NVIDIA , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066242985","display_name":"Bryan Catanzaro","orcid":"https://orcid.org/0000-0003-0034-7728","observed_orcids":["https://orcid.org/0000-0003-0034-7728"]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Catanzaro, Bryan","raw_affiliation_strings":["NVIDIA , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":152,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5669000148773193,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5669000148773193,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.179299995303154,"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/T11309","display_name":"Music and Audio Processing","score":0.15479999780654907,"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-language-models","display_name":"audio-language models","score":0.8059999942779541},{"id":"https://openalex.org/keywords/audio-understanding","display_name":"audio understanding","score":0.7480000257492065},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.800000011920929},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.9789999723434448},{"id":"https://openalex.org/keywords/audio-retrieval","display_name":"audio retrieval","score":0.5929999947547913},{"id":"https://openalex.org/keywords/multi-turn-dialogue","display_name":"multi-turn dialogue","score":0.9580000042915344},{"id":"https://openalex.org/keywords/non-speech-sounds","display_name":"non-speech sounds","score":0.6880000233650208},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6179999709129333},{"id":"https://openalex.org/keywords/multimodal-language-models","display_name":"multimodal language models","score":0.5809999704360962}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.70509934425354},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6898557543754578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47801506519317627},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3548504114151001},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35257482528686523},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3276897668838501},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.30261844396591187},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2402.01831","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.01831","pdf_url":"https://arxiv.org/pdf/2402.01831","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.01831","doi":"https://doi.org/10.48550/arxiv.2402.01831","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.01831","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:2402.01831","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.01831","pdf_url":"https://arxiv.org/pdf/2402.01831","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391591726.pdf","grobid_xml":"https://content.openalex.org/works/W4391591726.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W2580221632","https://openalex.org/W2810914326","https://openalex.org/W2895615590","https://openalex.org/W2908510526","https://openalex.org/W3015883388","https://openalex.org/W3017604292","https://openalex.org/W3102568015","https://openalex.org/W3109943296","https://openalex.org/W3146639881","https://openalex.org/W3158978276","https://openalex.org/W3198002980","https://openalex.org/W4229005866","https://openalex.org/W4293575120","https://openalex.org/W4297841687","https://openalex.org/W4307323391","https://openalex.org/W4312205996","https://openalex.org/W4318351475","https://openalex.org/W4318718936","https://openalex.org/W4323572061","https://openalex.org/W4327810158","https://openalex.org/W4366330503","https://openalex.org/W4377130946","https://openalex.org/W4377372369","https://openalex.org/W4378501696","https://openalex.org/W4379251869","https://openalex.org/W4380994269","https://openalex.org/W4381827575","https://openalex.org/W4385474092","https://openalex.org/W4385807453","https://openalex.org/W4385822467","https://openalex.org/W4386555501","https://openalex.org/W4387210470","https://openalex.org/W4387596061","https://openalex.org/W4387891768","https://openalex.org/W4388717464","https://openalex.org/W4388718054","https://openalex.org/W4392903210","https://openalex.org/W4392903872","https://openalex.org/W4392904213","https://openalex.org/W4392909390","https://openalex.org/W4392931630","https://openalex.org/W4393178509","https://openalex.org/W4393413574","https://openalex.org/W4393838864","https://openalex.org/W4400033239","https://openalex.org/W4401042775","https://openalex.org/W4402112279","https://openalex.org/W4402716264"],"related_works":["https://openalex.org/W6929354950","https://openalex.org/W4416112203","https://openalex.org/W7154207876","https://openalex.org/W7117988839","https://openalex.org/W4406794295","https://openalex.org/W4415797407","https://openalex.org/W7214809161","https://openalex.org/W4399795459","https://openalex.org/W4415433122","https://openalex.org/W4400104114"],"abstract_inverted_index":{"Augmenting":[0],"large":[1],"language":[2,35],"models":[3],"(LLMs)":[4],"to":[5,46,49,75],"understand":[6],"audio":[7,34,40,86],"--":[8,15],"including":[9],"non-speech":[10],"sounds":[11],"and":[12,55,57,72,104],"non-verbal":[13],"speech":[14],"is":[16,102,107],"critically":[17],"important":[18],"for":[19],"diverse":[20],"real-world":[21],"applications":[22],"of":[23,67,92],"LLMs.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"propose":[29],"Audio":[30],"Flamingo,":[31],"a":[32,65],"novel":[33],"model":[36,78],"with":[37,79],"1)":[38],"strong":[39,59],"understanding":[41,87],"abilities,":[42],"2)":[43],"the":[44,90,105],"ability":[45],"quickly":[47],"adapt":[48],"unseen":[50],"tasks":[51,88],"via":[52],"in-context":[53],"learning":[54],"retrieval,":[56],"3)":[58],"multi-turn":[60],"dialogue":[61],"abilities.":[62,81],"We":[63],"introduce":[64],"series":[66],"training":[68],"techniques,":[69],"architecture":[70],"design,":[71],"data":[73],"strategies":[74],"enhance":[76],"our":[77,93],"these":[80],"Extensive":[82],"evaluations":[83],"across":[84],"various":[85],"confirm":[89],"efficacy":[91],"method,":[94],"setting":[95],"new":[96],"state-of-the-art":[97],"benchmarks.":[98],"Our":[99],"demo":[100],"website":[101],"https://audioflamingo.github.io/":[103],"code":[106],"open-sourced":[108],"at":[109],"https://github.com/NVIDIA/audio-flamingo.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":61},{"year":2025,"cited_by_count":68},{"year":2024,"cited_by_count":23}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-02-07T00:00:00"}