{"id":"https://openalex.org/W4414231100","doi":"https://doi.org/10.1109/ialp68296.2024.11156308","title":"CoSSHI: LLM-Powered Large-Scale Multitask Hinglish Dataset for Speech Forensics","display_name":"CoSSHI: LLM-Powered Large-Scale Multitask Hinglish Dataset for Speech Forensics","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4414231100","doi":"https://doi.org/10.1109/ialp68296.2024.11156308"},"language":"en","primary_location":{"id":"doi:10.1109/ialp68296.2024.11156308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","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/A5013098603","display_name":"Nisarg Trivedi","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nisarg Trivedi","raw_affiliation_strings":["Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114974321","display_name":"Ravindrakumar M. Purohit","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ravindrakumar M. Purohit","raw_affiliation_strings":["Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101823773","display_name":"Satyam Tiwari","orcid":"https://orcid.org/0000-0002-3587-1805"},"institutions":[{"id":"https://openalex.org/I42014448","display_name":"Sardar Vallabhbhai National Institute of Technology Surat","ror":"https://ror.org/02y394t43","country_code":"IN","type":"education","lineage":["https://openalex.org/I42014448"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Satyam Tiwari","raw_affiliation_strings":["Sarvajanik College of Engineering and Technology (SCET),Surat,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sarvajanik College of Engineering and Technology (SCET),Surat,India","institution_ids":["https://openalex.org/I42014448"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11524504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"135","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9883000254631042,"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":0.9638000130653381,"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/stress","display_name":"Stress (linguistics)","score":0.7186999917030334},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5389000177383423},{"id":"https://openalex.org/keywords/lexical-diversity","display_name":"Lexical diversity","score":0.42100000381469727},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3894999921321869},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3271999955177307},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.3188999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238000273704529},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7186999917030334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5928000211715698},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5393999814987183},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5001999735832214},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.42100000381469727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41019999980926514},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.3188999891281128},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.30809998512268066},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp68296.2024.11156308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2176804518","https://openalex.org/W2194775991","https://openalex.org/W2895577402","https://openalex.org/W2963446712","https://openalex.org/W3095877226","https://openalex.org/W3115081393","https://openalex.org/W3163159230","https://openalex.org/W3213515747","https://openalex.org/W4293092748","https://openalex.org/W4381198892","https://openalex.org/W4402112533"],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"datasets":[1],"come":[2],"with":[3],"limited":[4],"diversity":[5],"in":[6,30,53],"terms":[7],"of":[8],"language":[9,60],"and":[10,17,45,82,117,140,145,147],"linguistic":[11],"features.":[12],"This":[13],"makes":[14],"them":[15],"language-biased":[16],"less":[18],"generalized":[19],"towards":[20],"other":[21,36],"languages.":[22],"In":[23,47],"another":[24],"way,":[25],"it":[26],"reduces":[27],"the":[28,35,40,51,58,91],"effectiveness":[29],"a":[31,62],"real-world":[32],"scenarios.":[33],"On":[34],"side,":[37],"manually":[38],"creating":[39],"dataset":[41,66,87,158],"is":[42,69,88,125],"time-consuming,":[43],"expensive,":[44],"resource-intensive.":[46],"order":[48],"to":[49,163],"minimize":[50],"limitation,":[52],"this":[54],"paper,":[55],"by":[56],"using":[57,90,130],"large":[59],"models,":[61],"largescale,":[63],"code-mixed":[64],"(English+Hindi)":[65],"called":[67],"CoSSHI":[68,124],"created":[70,89],"for":[71,136,142,150],"various":[72,128],"tasks,":[73],"such":[74,133],"as":[75,134],"deepfake":[76,137],"detection,":[77,138],"accent":[78,143],"identification":[79],"(60+":[80],"hours),":[81],"speech":[83,151],"synthesis.":[84,152],"The":[85,153],"proposed":[86],"state-of-the-art":[92],"LLM":[93],"models":[94,106],"(e.g.,":[95],"GPT-4o,":[96],"Gemini":[97],"2.5":[98],"Pro,":[99],"Grok-3,":[100],"Mistral":[101],"Large,":[102],"Llama":[103],"4),":[104],"text-to-speech":[105],"(160+":[107],"hours,":[108,120],"e.g.,":[109,121],"XTTSv2,":[110],"XTTSv1.1,":[111],"Bark,":[112],"gTTS,":[113],"IndicTTS,":[114],"YoursTTS,":[115],"VITS),":[116],"vocoder":[118],"(320+":[119],"HiFiGAN,":[122],"BigVGAN).":[123],"evaluated":[126],"on":[127],"tasks":[129],"different":[131],"measures,":[132],"precision":[135,141],"accuracy":[139],"identification,":[144],"subjective":[146],"objective":[148],"measures":[149],"results":[154],"indicate":[155],"that":[156],"our":[157],"offers":[159],"competitive":[160],"performance":[161],"compared":[162],"existing":[164],"datasets.":[165]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}