{"id":"https://openalex.org/W4408352823","doi":"https://doi.org/10.1109/icassp49660.2025.10887667","title":"Hierarchical Loss for Bi-Level Classification of Speech into Language and Dialects","display_name":"Hierarchical Loss for Bi-Level Classification of Speech into Language and Dialects","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352823","doi":"https://doi.org/10.1109/icassp49660.2025.10887667"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887667","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/A5093307107","display_name":"Ananya Angra","orcid":null},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ananya Angra","raw_affiliation_strings":["SCEE Indian Institute of Technology Mandi,MANAS Lab,Mandi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SCEE Indian Institute of Technology Mandi,MANAS Lab,Mandi,India","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080489693","display_name":"H Muralikrishna","orcid":"https://orcid.org/0000-0002-6340-4227"},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Muralikrishna H","raw_affiliation_strings":["Manipal Academy of Higher Education,Manipal Institute of Technology,Department of Electronics and Communication Engineering,Manipal,India,576104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manipal Academy of Higher Education,Manipal Institute of Technology,Department of Electronics and Communication Engineering,Manipal,India,576104","institution_ids":["https://openalex.org/I164861460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112944102","display_name":"A. D. Dileep","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dileep A. D.","raw_affiliation_strings":["Indian Institute of Technology Dharwad,Department of Computer Science Engineering,Dharwad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Department of Computer Science Engineering,Dharwad,India","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080105717","display_name":"Veena Thenkanidiyoor","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109276","display_name":"National Institute of Technology Goa","ror":"https://ror.org/01vmfpj79","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210109276"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Veena Thenkanidiyoor","raw_affiliation_strings":["National Institute of Technology Goa,Department of Computer Science Engineering,Goa,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Goa,Department of Computer Science Engineering,Goa,India","institution_ids":["https://openalex.org/I4210109276"]}]}],"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":0.02574796,"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":0.7125999927520752,"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":0.7125999927520752,"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":0.7256675958633423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5352488160133362},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4487822353839874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42642679810523987},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3379245698451996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7256675958633423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5352488160133362},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4487822353839874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42642679810523987},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3379245698451996},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887667","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":[{"score":0.5199999809265137,"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":20,"referenced_works":["https://openalex.org/W2118112131","https://openalex.org/W2807627734","https://openalex.org/W2890964092","https://openalex.org/W2937548051","https://openalex.org/W2962922562","https://openalex.org/W2963134917","https://openalex.org/W3007260291","https://openalex.org/W3035406632","https://openalex.org/W3041618382","https://openalex.org/W3046054871","https://openalex.org/W3159838843","https://openalex.org/W3162885496","https://openalex.org/W4224031782","https://openalex.org/W4226380987","https://openalex.org/W4283820491","https://openalex.org/W4297859492","https://openalex.org/W4385783931","https://openalex.org/W4388854264","https://openalex.org/W4388878822","https://openalex.org/W6780218876"],"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/W3204019825"],"abstract_inverted_index":{"Spoken":[0],"dialect":[1,177,183,223,241],"identification":[2,87],"(DID)":[3],"is":[4,41,146,235],"a":[5,26,168,176,182,185,194,221,252],"challenging":[6],"task":[7],"due":[8],"to":[9,22,51,61,124,139,163,202,245,266],"high":[10],"similarities":[11,166],"between":[12,66,128,207],"the":[13,37,58,63,67,85,100,106,113,122,126,154,161,200,204,213,225,229,246,269],"classes.":[14],"This":[15],"becomes":[16],"further":[17],"complicated":[18],"when":[19,30,239],"DID":[20,59,90,107,143],"needs":[21],"be":[23],"performed":[24],"in":[25,79,110,153,167,268],"multi-lingual":[27],"environment,":[28],"especially":[29],"languages":[31,68,152,258],"are":[32],"from":[33,178],"same":[34],"language-family,":[35],"as":[36],"scope":[38],"for":[39],"confusion":[40],"significantly":[42],"high.":[43],"In":[44],"this":[45,53,135,190],"paper,":[46],"we":[47,83,137,192],"propose":[48,138,193],"multiple":[49],"techniques":[50,56],"address":[52,189],"issue.":[54],"These":[55],"motivate":[57],"system":[60],"respect":[62],"parent-child":[64,205,233],"relationship":[65,206,234],"and":[69,89,93,209,220],"their":[70],"dialects":[71,129,149],"by":[72],"performing":[73],"bi-level":[74],"classification":[75],"of":[76,102,130,150,184,215,254],"speech.":[77],"Specifically,":[78,211],"our":[80],"first":[81],"approach,":[82],"train":[84,140],"language":[86,208,218],"(LID)":[88],"models":[91],"independently":[92],"then":[94],"combine":[95],"them":[96],"together":[97],"such":[98,116,157],"that":[99,260],"output":[101],"LID":[103],"model":[104,123,144,162,201,230],"selects":[105],"model,":[108],"which":[109,145,198],"turn":[111],"decides":[112],"dialect.":[114],"However,":[115],"independent":[117],"training":[118,159,264],"does":[119,172,242],"not":[120,173,236,243],"allow":[121],"learn":[125,164],"relations/similarities":[127],"different":[131,186],"languages.":[132],"To":[133,188],"overcome":[134],"limitation,":[136,191],"an":[141,216],"end-to-end":[142,158],"trained":[147],"using":[148],"all":[151],"dataset.":[155],"While":[156],"allows":[160],"inter-dialect":[165],"better":[169],"way,":[170],"it":[171],"explicitly":[174],"prevent":[175],"being":[179],"misclassified":[180],"into":[181],"language.":[187,248],"novel":[195],"hierarchical":[196,226,261],"loss,":[197],"motivates":[199],"maintain":[203],"dialects.":[210],"with":[212],"help":[214],"auxiliary":[217],"classifier":[219],"primary":[222],"classifier,":[224],"loss":[227,262],"penalizes":[228],"heavily":[231],"whenever":[232],"maintained,":[237],"i.e.,":[238],"predicted":[240,247],"belong":[244],"Experiments":[249],"conducted":[250],"on":[251],"set":[253],"closely":[255],"related":[256],"Indian":[257],"shows":[259],"based":[263],"leads":[265],"improvement":[267],"performance.":[270]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}