{"id":"https://openalex.org/W3008749227","doi":"https://doi.org/10.1109/asru46091.2019.9004000","title":"Speaker and Language Aware Training for End-to-End ASR","display_name":"Speaker and Language Aware Training for End-to-End ASR","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008749227","doi":"https://doi.org/10.1109/asru46091.2019.9004000","mag":"3008749227"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9004000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004000","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5114889726","display_name":"Shubham Bansal","orcid":"https://orcid.org/0000-0002-8754-1074"},"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":"Shubham Bansal","raw_affiliation_strings":["Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076166361","display_name":"Karan Malhotra","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":"Karan Malhotra","raw_affiliation_strings":["Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"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":"Sriram Ganapathy","raw_affiliation_strings":["Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.5467,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73215926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"ldc94s13a","issue":null,"first_page":"494","last_page":"501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","score":0.9926999807357788,"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":0.991599977016449,"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":0.7878814935684204},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.646770715713501},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6420040726661682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5575237274169922},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4126219153404236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3013068437576294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878814935684204},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.646770715713501},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6420040726661682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5575237274169922},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4126219153404236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3013068437576294},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru46091.2019.9004000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004000","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:65001","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1915251500","https://openalex.org/W1995752403","https://openalex.org/W2002342963","https://openalex.org/W2079623482","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2160306971","https://openalex.org/W2164240571","https://openalex.org/W2250357346","https://openalex.org/W2327501763","https://openalex.org/W2398776621","https://openalex.org/W2545177271","https://openalex.org/W2577366047","https://openalex.org/W2597757402","https://openalex.org/W2766219058","https://openalex.org/W2787663903","https://openalex.org/W2799800213","https://openalex.org/W2886180730","https://openalex.org/W2888779557","https://openalex.org/W2889374926","https://openalex.org/W2889519245","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963070863","https://openalex.org/W2963174344","https://openalex.org/W2963362078","https://openalex.org/W2963403868","https://openalex.org/W2963418523","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6691509046","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"The":[0,33],"end-to-end":[1,37,76],"(E2E)":[2],"approach":[3,15,35],"to":[4,29,36,61,117,133],"automatic":[5],"speech":[6],"recognition":[7],"(ASR)":[8],"is":[9,83,103],"a":[10,17,58,71],"simplified":[11],"and":[12,107,145,154],"an":[13,50,119],"elegant":[14],"where":[16,79],"single":[18],"deep":[19],"neural":[20,41,101],"network":[21,42,102],"model":[22,43,55,89,111,128],"directly":[23],"converts":[24],"the":[25,30,40,63,80,87,100,110,126,131,151,159,164,170],"acoustic":[26],"feature":[27,124],"sequence":[28,46,122],"text":[31,64],"sequence.":[32,65],"current":[34],"ASR":[38,77,127,140,160],"uses":[39],"(trained":[44],"with":[45,49],"loss)":[47],"along":[48],"external":[51],"character/word":[52],"based":[53,121],"language":[54],"(LM)":[56],"in":[57,86,125],"decoding":[59],"pass":[60],"output":[62],"In":[66,97],"this":[67,98,108],"work,":[68],"we":[69,148],"propose":[70,116],"new":[72],"objective":[73],"function":[74,91],"for":[75,175],"training":[78,95,112,157],"LM":[81,105,155],"score":[82],"explicitly":[84],"introduced":[85],"attention":[88,120],"loss":[90],"without":[92],"any":[93],"additional":[94],"parameters.":[96],"manner,":[99],"made":[104],"aware":[106,156],"simplifies":[109],"process.":[113],"We":[114,168],"also":[115],"incorporate":[118],"summary":[123],"which":[129],"allows":[130],"system":[132],"be":[134],"speaker":[135,153],"aware.":[136],"With":[137],"several":[138],"E2E":[139,166],"experiments":[141],"on":[142],"TED-LIUM,":[143],"WSJ":[144,176],"Librispeech":[146],"datasets,":[147],"show":[149],"that":[150],"proposed":[152],"improves":[158],"performance":[161],"significantly":[162],"over":[163],"state-of-art":[165],"approaches.":[167],"achieve":[169],"best":[171],"published":[172],"results":[173],"reported":[174],"dataset.":[177]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}