{"id":"https://openalex.org/W4410771957","doi":"https://doi.org/10.1109/icasspw65056.2025.11011192","title":"IndicST: Indian Multilingual Translation Corpus For Evaluating Speech Large Language Models","display_name":"IndicST: Indian Multilingual Translation Corpus For Evaluating Speech Large Language Models","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410771957","doi":"https://doi.org/10.1109/icasspw65056.2025.11011192"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5006107552","display_name":"Sanket Shah","orcid":"https://orcid.org/0000-0002-0617-6061"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sanket Shah","raw_affiliation_strings":["Krutrim AI,Bangalore"],"affiliations":[{"raw_affiliation_string":"Krutrim AI,Bangalore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008569069","display_name":"Kavya Ranjan Saxena","orcid":"https://orcid.org/0000-0002-6590-2019"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kavya Ranjan Saxena","raw_affiliation_strings":["IIT Kanpur"],"affiliations":[{"raw_affiliation_string":"IIT Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001376003","display_name":"Kancharana Manideep Bharadwaj","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kancharana Manideep Bharadwaj","raw_affiliation_strings":["Krutrim AI,Bangalore"],"affiliations":[{"raw_affiliation_string":"Krutrim AI,Bangalore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054490307","display_name":"Sharath Adavanne","orcid":"https://orcid.org/0000-0002-5001-6911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharath Adavanne","raw_affiliation_strings":["Krutrim AI,Bangalore"],"affiliations":[{"raw_affiliation_string":"Krutrim AI,Bangalore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015353805","display_name":"Nagaraj Adiga","orcid":"https://orcid.org/0000-0002-3438-567X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nagaraj Adiga","raw_affiliation_strings":["Krutrim AI,Bangalore"],"affiliations":[{"raw_affiliation_string":"Krutrim AI,Bangalore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006107552"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05962467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9952999949455261,"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":0.9952999949455261,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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":0.9638000130653381,"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":0.7961457371711731},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.690764844417572},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6590688228607178},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6119107007980347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.589126467704773},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5549545288085938},{"id":"https://openalex.org/keywords/language-translation","display_name":"Language translation","score":0.4367940127849579},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4254283010959625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41123324632644653},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.33932244777679443},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2677154541015625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961457371711731},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.690764844417572},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6590688228607178},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6119107007980347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.589126467704773},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5549545288085938},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.4367940127849579},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4254283010959625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41123324632644653},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33932244777679443},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2677154541015625},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2404169761","https://openalex.org/W3147984406","https://openalex.org/W4251372957","https://openalex.org/W4319862635","https://openalex.org/W4372267440","https://openalex.org/W4378505287","https://openalex.org/W4382202628","https://openalex.org/W4385822371","https://openalex.org/W4387946866","https://openalex.org/W4389519587","https://openalex.org/W4389524500","https://openalex.org/W4402111367","https://openalex.org/W4402112143","https://openalex.org/W4402670026","https://openalex.org/W4404781855","https://openalex.org/W6767671539","https://openalex.org/W6771467084","https://openalex.org/W6776605602","https://openalex.org/W6796581206","https://openalex.org/W6810007534","https://openalex.org/W6847363464","https://openalex.org/W6848208918","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6852326057","https://openalex.org/W6852447913","https://openalex.org/W6853094705","https://openalex.org/W6853249747","https://openalex.org/W6853937136","https://openalex.org/W6853998256","https://openalex.org/W6857054612","https://openalex.org/W6859099255","https://openalex.org/W6870283767"],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2969905756","https://openalex.org/W4362498905","https://openalex.org/W2338806053","https://openalex.org/W2000013842","https://openalex.org/W1489621819","https://openalex.org/W4362495644","https://openalex.org/W2163485403","https://openalex.org/W2909367404"],"abstract_inverted_index":{"The":[0,81],"integration":[1],"of":[2,17,86,92,116,134,144],"speech":[3,23,28,109],"modalities":[4],"into":[5],"large":[6],"language":[7],"models,":[8],"known":[9],"as":[10],"Speech":[11,63,118],"LLMs,":[12],"is":[13,38],"a":[14,39,55,98],"promising":[15],"area":[16],"research":[18,146],"for":[19,35,42,59,65,107,153],"applications":[20],"like":[21],"automatic":[22,27],"recognition":[24],"(ASR)":[25],"and":[26,61,70,76,89,122,150],"translation":[29],"(AST).":[30],"While":[31],"several":[32],"datasets":[33],"exist":[34],"ASR,":[36],"there":[37],"critical":[40],"gap":[41],"AST":[43,66,123,151],"tasks":[44,67],"in":[45,147],"Indian":[46,154],"languages.":[47,155],"To":[48],"fill":[49],"this":[50],"gap,":[51],"we":[52,96],"introduce":[53],"IndicST,":[54],"new":[56],"dataset":[57,82],"tailored":[58],"training":[60,87],"evaluating":[62],"LLMs":[64,119],"(including":[68],"ASR":[69,121,149],"TTS),":[71],"featuring":[72],"meticulously":[73],"curated,":[74],"automatically":[75],"manually":[77],"verified":[78],"synthetic":[79],"data.":[80,94],"offers":[83],"10.8k":[84],"hrs":[85,91],"data":[88,100],"1.13k":[90],"evaluation":[93],"Additionally,":[95],"present":[97],"scalable":[99],"collection":[101],"methodology":[102],"that":[103],"allows":[104],"easy":[105],"development":[106],"other":[108],"tasks.":[110],"Our":[111],"analysis":[112],"examines":[113],"the":[114,132,141],"performance":[115,133],"various":[117],"on":[120],"tasks,":[124],"accompanied":[125],"by":[126],"insightful":[127],"findings.":[128],"We":[129],"also":[130],"explore":[131],"these":[135],"models":[136],"across":[137],"different":[138],"prompts,":[139],"highlighting":[140],"significant":[142],"potential":[143],"our":[145],"enhancing":[148],"capabilities":[152]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
