{"id":"https://openalex.org/W7148468420","doi":"https://doi.org/10.1109/asru65441.2025.11434596","title":"Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data","display_name":"Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148468420","doi":"https://doi.org/10.1109/asru65441.2025.11434596"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048139334","display_name":"Gokul Karthik Kumar","orcid":"https://orcid.org/0000-0003-2848-7095"},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Gokul Karthik Kumar","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052740794","display_name":"Rishabh Saraf","orcid":"https://orcid.org/0000-0001-7830-423X"},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Rishabh Saraf","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020952319","display_name":"Ludovick Lepauloux","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ludovick Lepauloux","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132798215","display_name":"Abdul Muneer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Abdul Muneer","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120324509","display_name":"Billel Mokeddem","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Billel Mokeddem","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013316111","display_name":"Hakim Hacid","orcid":"https://orcid.org/0000-0003-2265-9343"},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Hakim Hacid","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048139334"],"corresponding_institution_ids":["https://openalex.org/I4210087059"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85877355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.16840000450611115,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.16840000450611115,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.09650000184774399,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06300000101327896,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5827999711036682},{"id":"https://openalex.org/keywords/centrality","display_name":"Centrality","score":0.5756999850273132},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5002999901771545},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44440001249313354},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.39730000495910645},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3747999966144562},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3702999949455261},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.3508000075817108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6061000227928162},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C53811970","wikidata":"https://www.wikidata.org/wiki/Q5062194","display_name":"Centrality","level":2,"score":0.5756999850273132},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44769999384880066},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3871999979019165},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C58546491","wikidata":"https://www.wikidata.org/wiki/Q1150207","display_name":"Competitive advantage","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25540000200271606},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6578060388565063}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2726515241","https://openalex.org/W2945761034","https://openalex.org/W2972359262","https://openalex.org/W3015371781","https://openalex.org/W3176445421","https://openalex.org/W3196974791","https://openalex.org/W4205689591","https://openalex.org/W4372266552","https://openalex.org/W4385807453","https://openalex.org/W4386071707","https://openalex.org/W4390873312","https://openalex.org/W4391021627","https://openalex.org/W4392909390","https://openalex.org/W4401044042","https://openalex.org/W4402684170","https://openalex.org/W4402727764","https://openalex.org/W4404575065","https://openalex.org/W4404784428","https://openalex.org/W7133196460","https://openalex.org/W7133212838"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,58,93,128],"(LLMs)":[3],"have":[4],"transformed":[5],"NLP,":[6],"yet":[7],"their":[8],"integration":[9],"with":[10,63,90],"audio":[11,42,114],"remains":[12,88],"underex-plored-despite":[13],"audio\u2019s":[14],"centrality":[15],"to":[16,98,127],"human":[17],"communication.":[18],"We":[19],"introduce":[20],"Falcon3-Audio,":[21],"a":[22,36,64],"family":[23],"of":[24,40,66,137],"Audio-Language":[25],"Models":[26],"(ALMs)":[27],"built":[28],"on":[29,59,130],"instruction-tuned":[30],"LLMs":[31],"and":[32,76,81,116],"Whisper":[33],"encoders.":[34],"Using":[35],"remarkably":[37],"small":[38],"amount":[39],"public":[41],"data-less":[43],"than":[44],"30":[45],"K":[46,49],"hours":[47,136],"(5":[48],"unique)-Falcon3-Audio-7B":[50],"matches":[51],"the":[52,60],"best":[53],"reported":[54],"performance":[55],"among":[56],"open-weight":[57],"MMAU":[61],"benchmark,":[62],"score":[65],"64.14,":[67],"matching":[68],"R1-AQA,":[69],"while":[70],"distinguishing":[71],"itself":[72],"through":[73],"superior":[74],"data":[75],"parameter":[77],"efficiency,":[78],"single-stage":[79],"training,":[80],"transparency.":[82],"Notably,":[83],"our":[84],"smallest":[85],"1B":[86],"model":[87],"competitive":[89],"larger":[91],"open":[92],"ranging":[94],"from":[95],"2":[96],"B":[97,100],"13":[99],"parameters.":[101],"Through":[102],"extensive":[103],"ablations,":[104],"we":[105],"find":[106],"that":[107],"common":[108],"complexities-such":[109],"as":[110],"curriculum":[111],"learning,":[112],"multiple":[113],"encoders,":[115],"intricate":[117],"cross-attention":[118],"connec-tors-are":[119],"not":[120],"required":[121],"for":[122],"strong":[123],"performance,":[124],"even":[125],"compared":[126],"trained":[129],"over":[131],"$\\mathbf{5":[132],"0":[133,134],"K}$":[135],"data.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}
