{"id":"https://openalex.org/W4391021363","doi":"https://doi.org/10.1109/asru57964.2023.10389624","title":"Gated Multi Encoders and Multitask Objectives for Dialectal Speech Recognition in Indian Languages","display_name":"Gated Multi Encoders and Multitask Objectives for Dialectal Speech Recognition in Indian Languages","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021363","doi":"https://doi.org/10.1109/asru57964.2023.10389624"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mpra.ub.uni-muenchen.de/84555/1/MPRA_paper_84555.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023703313","display_name":"Sathvik Udupa","orcid":"https://orcid.org/0000-0002-2225-5464"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sathvik Udupa","raw_affiliation_strings":["Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092491177","display_name":"Jesuraja Bandekar","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jesuraja Bandekar","raw_affiliation_strings":["Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013741629","display_name":"G Deekshitha","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"G Deekshitha","raw_affiliation_strings":["Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106943708","display_name":"Saurabh Kumar","orcid":"https://orcid.org/0000-0003-1825-5178"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Saurabh Kumar","raw_affiliation_strings":["Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101685661","display_name":"Prasanta Kumar Ghosh","orcid":"https://orcid.org/0000-0002-1137-0838"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prasanta Kumar Ghosh","raw_affiliation_strings":["Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111010497","display_name":"Sandhya Badiger","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandhya Badiger","raw_affiliation_strings":["Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064971186","display_name":"Abhayjeet Singh","orcid":"https://orcid.org/0000-0002-8512-8083"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhayjeet Singh","raw_affiliation_strings":["Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084244030","display_name":"Savitha Murthy","orcid":"https://orcid.org/0000-0001-7560-0420"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Savitha Murthy","raw_affiliation_strings":["Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114218700","display_name":"Priyanka Pai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Priyanka Pai","raw_affiliation_strings":["Navana Tech (NT),Mumbai,India,400001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navana Tech (NT),Mumbai,India,400001","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069852433","display_name":"Srinivasa R. Raghavan","orcid":"https://orcid.org/0000-0003-0710-9845"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srinivasa Raghavan","raw_affiliation_strings":["Navana Tech (NT),Mumbai,India,400001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navana Tech (NT),Mumbai,India,400001","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004861194","display_name":"Raoul Nanavati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raoul Nanavati","raw_affiliation_strings":["Navana Tech (NT),Mumbai,India,400001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navana Tech (NT),Mumbai,India,400001","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6345,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74673122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9958000183105469,"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/bengali","display_name":"Bengali","score":0.9236307144165039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8091521263122559},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7135339379310608},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6604812145233154},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6531404852867126},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6390321850776672},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5258179903030396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5184828639030457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5023198127746582},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4665828347206116},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4608660638332367},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06776133179664612},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06450212001800537},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.059235453605651855}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9236307144165039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091521263122559},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7135339379310608},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6604812145233154},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6531404852867126},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6390321850776672},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5258179903030396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5184828639030457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023198127746582},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4665828347206116},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4608660638332367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06776133179664612},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06450212001800537},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.059235453605651855},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru57964.2023.10389624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai::84555","is_oa":true,"landing_page_url":"https://eprints.iisc.ac.in/84555/1/Aut_spe_rec_und_wor_asr_2023","pdf_url":"https://mpra.ub.uni-muenchen.de/84555/1/MPRA_paper_84555.pdf","source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai::84555","is_oa":true,"landing_page_url":"https://eprints.iisc.ac.in/84555/1/Aut_spe_rec_und_wor_asr_2023","pdf_url":"https://mpra.ub.uni-muenchen.de/84555/1/MPRA_paper_84555.pdf","source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391021363.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2084665283","https://openalex.org/W2327501763","https://openalex.org/W2591804103","https://openalex.org/W2766219058","https://openalex.org/W2899640612","https://openalex.org/W2933138175","https://openalex.org/W2962780374","https://openalex.org/W2962893195","https://openalex.org/W3016010032","https://openalex.org/W3036601975","https://openalex.org/W3096122506","https://openalex.org/W3097306574","https://openalex.org/W3097777922","https://openalex.org/W3162227798","https://openalex.org/W3197140813","https://openalex.org/W3198275944","https://openalex.org/W3198871389","https://openalex.org/W3205032693","https://openalex.org/W3212767696","https://openalex.org/W3213618310","https://openalex.org/W4281770669","https://openalex.org/W4285044984","https://openalex.org/W4287075881","https://openalex.org/W4287888308","https://openalex.org/W4296068832","https://openalex.org/W4296070193","https://openalex.org/W4311000453","https://openalex.org/W4372259817","https://openalex.org/W4372262650","https://openalex.org/W4378105483","https://openalex.org/W4384644122","https://openalex.org/W4385807424","https://openalex.org/W4385822416","https://openalex.org/W4390678101","https://openalex.org/W4391021732","https://openalex.org/W6679855610","https://openalex.org/W6780218876","https://openalex.org/W6802842272","https://openalex.org/W6850439986"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W4298170800","https://openalex.org/W2895890526","https://openalex.org/W617692174","https://openalex.org/W2794758919","https://openalex.org/W4232781930","https://openalex.org/W1913642778","https://openalex.org/W2630858571","https://openalex.org/W4300860228","https://openalex.org/W2329406070"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"several":[3],"methods":[4],"have":[5,80],"been":[6,23,61,81],"proposed":[7,92],"towards":[8],"improving":[9,122],"the":[10,46,55,76,91],"performance":[11,56,123],"of":[12,48,57,66,75,99],"dialectal":[13,58],"automatic":[14],"speech":[15],"recognition":[16],"(ASR).":[17],"A":[18],"novel":[19],"encoder":[20],"architecture":[21],"has":[22,60],"introduced":[24],"that":[25,90],"is":[26],"suited":[27],"for":[28],"multi-dialect":[29],"ASR":[30,59,94],"training.":[31],"Further,":[32],"we":[33,111,128],"propose":[34],"Multi-Task":[35],"Self-Supervised":[36],"learning":[37],"(SSL)":[38],"fine-tuning":[39,119],"using":[40,132],"CTC":[41],"and":[42,68,101,107],"dialect":[43],"identification.":[44],"Additionally,":[45,110],"use":[47],"different":[49],"language":[50],"models":[51],"(LM)":[52],"to":[53,83],"improve":[54],"investigated.":[62],"Around":[63],"800":[64],"hours":[65],"Bengali":[67],"Bhojpuri":[69,106],"data,":[70],"released":[71],"as":[72],"a":[73,96,114],"part":[74],"MADASR":[77],"ASRU":[78],"challenge":[79],"used":[82],"train":[84],"these":[85,125],"models.":[86],"The":[87],"work":[88],"shows":[89],"multi-encoder":[93],"observes":[95],"relative":[97],"reduction":[98,117],"7.5%":[100],"9%":[102],"in":[103,105,118,124,131],"WER":[104,116],"Bengali,":[108],"respectively.":[109],"also":[112],"observe":[113,129],"1-2%":[115],"SSL,":[120],"further":[121],"languages.":[126],"Moreover,":[127],"advantages":[130],"dialect-specific":[133],"LM":[134],"decoding":[135],"based":[136],"on":[137],"predicted":[138],"dialect.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}