{"id":"https://openalex.org/W4408356206","doi":"https://doi.org/10.1109/icassp49660.2025.10889964","title":"Can RAG-Driven Enhancements Amplify Audio LLMs for Low-Resource Languages?","display_name":"Can RAG-Driven Enhancements Amplify Audio LLMs for Low-Resource Languages?","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356206","doi":"https://doi.org/10.1109/icassp49660.2025.10889964"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102635118","display_name":"Bikash Dutta","orcid":null},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bikash Dutta","raw_affiliation_strings":["Indian Institute of Technology,Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110852852","display_name":"Rishabh Ranjan","orcid":null},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rishabh Ranjan","raw_affiliation_strings":["Indian Institute of Technology,Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012473597","display_name":"Akshat Jain","orcid":"https://orcid.org/0000-0001-9194-555X"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Akshat Jain","raw_affiliation_strings":["Indian Institute of Technology,Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101477779","display_name":"Richa Singh","orcid":"https://orcid.org/0000-0002-9391-958X"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Richa Singh","raw_affiliation_strings":["Indian Institute of Technology,Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050521702","display_name":"Mayank Vatsa","orcid":"https://orcid.org/0000-0001-5952-2274"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mayank Vatsa","raw_affiliation_strings":["Indian Institute of Technology,Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154549908"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.983299970626831,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.983299970626831,"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/T13999","display_name":"Digital Rights Management and Security","score":0.9125000238418579,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9103999733924866,"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/computer-science","display_name":"Computer science","score":0.596112847328186},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4915948808193207},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1274648904800415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.596112847328186},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4915948808193207},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1274648904800415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W4297841687","https://openalex.org/W4385570009","https://openalex.org/W4389524500","https://openalex.org/W4391021627","https://openalex.org/W4404784428","https://openalex.org/W6777615688","https://openalex.org/W6810738896","https://openalex.org/W6847363464","https://openalex.org/W6852264073","https://openalex.org/W6852818750","https://openalex.org/W6853249747","https://openalex.org/W6856227084","https://openalex.org/W6861152725","https://openalex.org/W6861264289"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"proliferation":[1],"of":[2,68,121],"Large":[3,30],"Language":[4,10,32],"Models":[5,33],"(LLMs)":[6],"has":[7,16],"transformed":[8],"Natural":[9],"Processing":[11],"(NLP),":[12],"yet":[13],"their":[14],"development":[15],"largely":[17],"overlooked":[18],"low-resource":[19,78,125],"languages.":[20],"This":[21,113],"paper":[22],"addresses":[23],"this":[24],"disparity":[25],"by":[26],"evaluating":[27],"three":[28],"prominent":[29],"Audio":[31,48],"(LALMs)":[34],"\u2013":[35,40],"LTU-AS,":[36],"GAMA,":[37],"and":[38,52,58,97,127,135],"Pengi":[39],"across":[41,111],"tasks":[42,55],"like":[43],"Automatic":[44],"Speech":[45],"Recognition":[46],"(ASR),":[47],"Question":[49],"Answering":[50],"(AQA),":[51],"audio":[53,91,105],"classification":[54,92],"in":[56,76,90],"Hindi":[57],"code-mixed":[59],"Hindi-English":[60],"(aka":[61],"Hinglish).":[62],"We":[63],"also":[64],"explore":[65],"the":[66,119],"potential":[67],"Retrieval-Augmented":[69],"Generation":[70],"(RAG)":[71],"to":[72],"boost":[73],"LALM":[74],"performance":[75,84],"these":[77],"settings.":[79],"Our":[80],"findings":[81],"highlight":[82],"significant":[83],"discrepancies,":[85],"with":[86,95],"LALMs":[87,123],"performing":[88],"well":[89],"but":[93],"struggling":[94],"ASR":[96],"AQA.":[98],"While":[99],"RAG":[100],"shows":[101],"potential,":[102],"especially":[103],"for":[104,124,131,139],"classification,":[106],"its":[107],"impact":[108],"is":[109],"inconsistent":[110],"tasks.":[112,142],"work":[114],"offers":[115],"critical":[116],"insights":[117],"into":[118],"challenges":[120],"using":[122],"languages":[126],"provides":[128],"a":[129],"foundation":[130],"developing":[132],"more":[133],"inclusive":[134],"adaptable":[136],"AI":[137],"systems":[138],"complex":[140],"multilingual":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}