{"id":"https://openalex.org/W3162471442","doi":"https://doi.org/10.1109/icassp39728.2021.9414703","title":"Task Aware Multi-Task Learning for Speech to Text Tasks","display_name":"Task Aware Multi-Task Learning for Speech to Text Tasks","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162471442","doi":"https://doi.org/10.1109/icassp39728.2021.9414703","mag":"3162471442"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5052409554","display_name":"Sathish Reddy Indurthi","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sathish Indurthi","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060189444","display_name":"Mohd Abbas Zaidi","orcid":"https://orcid.org/0000-0003-2961-4404"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mohd Abbas Zaidi","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007209790","display_name":"Nikhil Kumar Lakumarapu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nikhil Kumar Lakumarapu","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101981867","display_name":"Beomseok Lee","orcid":"https://orcid.org/0000-0003-3823-5502"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Beomseok Lee","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080589950","display_name":"HyoJung Han","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyojung Han","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022869420","display_name":"Seokchan Ahn","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokchan Ahn","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100761049","display_name":"Sang\u2010Ha Kim","orcid":"https://orcid.org/0000-0001-7231-8163"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangha Kim","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684416","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0001-9914-313X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101882326","display_name":"In-Chul Hwang","orcid":"https://orcid.org/0000-0002-0045-9984"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inchul Hwang","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":2.2385,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89878217,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7723","last_page":"7727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9995999932289124,"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":0.9987000226974487,"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":0.9987000226974487,"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":0.8274263739585876},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7877725958824158},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5389907956123352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5271204113960266},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.5073050856590271},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5004253387451172},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4360825717449188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3762784004211426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8274263739585876},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7877725958824158},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5389907956123352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5271204113960266},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.5073050856590271},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5004253387451172},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4360825717449188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3762784004211426},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1902237438","https://openalex.org/W2295072214","https://openalex.org/W2604763608","https://openalex.org/W2760103357","https://openalex.org/W2799473636","https://openalex.org/W2806412155","https://openalex.org/W2913340405","https://openalex.org/W2945700568","https://openalex.org/W2962784628","https://openalex.org/W2963403868","https://openalex.org/W2963532001","https://openalex.org/W2963993537","https://openalex.org/W2964093309","https://openalex.org/W2964309797","https://openalex.org/W2972451902","https://openalex.org/W2989384871","https://openalex.org/W3015633994","https://openalex.org/W3015698636","https://openalex.org/W3030437843","https://openalex.org/W3038092046","https://openalex.org/W3096490862","https://openalex.org/W3101648800","https://openalex.org/W4300558631","https://openalex.org/W4385245566","https://openalex.org/W6736057607","https://openalex.org/W6739901393","https://openalex.org/W6752136759","https://openalex.org/W6771467084","https://openalex.org/W6780516901"],"related_works":["https://openalex.org/W3196817267","https://openalex.org/W1564680838","https://openalex.org/W2003125260","https://openalex.org/W2060591604","https://openalex.org/W2951720331","https://openalex.org/W2166791242","https://openalex.org/W3012440055","https://openalex.org/W2585162246","https://openalex.org/W2034202275","https://openalex.org/W1934413089"],"abstract_inverted_index":{"In":[0],"general,":[1],"the":[2,21,24,30,44,53,61,114,119],"direct":[3],"Speech-to-text":[4],"translation":[5],"(ST)":[6],"is":[7],"jointly":[8],"trained":[9],"with":[10,23],"Automatic":[11],"Speech":[12],"Recognition":[13],"(ASR),":[14],"and":[15],"Machine":[16],"Translation":[17],"(MT)":[18],"tasks.":[19,35,76],"However,":[20],"issues":[22],"current":[25],"joint":[26],"learning":[27,52],"strategies":[28],"inhibit":[29],"knowledge":[31],"transfer":[32],"across":[33],"these":[34,75],"We":[36],"propose":[37],"a":[38,69,81,108],"task":[39,48,116],"modulation":[40],"network":[41],"which":[42,72],"allows":[43],"model":[45,71,79],"to":[46],"learn":[47],"specific":[49],"features,":[50],"while":[51,117],"shared":[54],"features":[55],"simultaneously.":[56],"This":[57,77,106],"proposed":[58],"approach":[59],"removes":[60],"need":[62],"for":[63],"separate":[64],"finetuning":[65],"step":[66],"resulting":[67],"in":[68],"single":[70,78],"performs":[73],"all":[74],"achieves":[80],"performance":[82,111],"of":[83,92],"28.64":[84],"BLEU":[85,99],"score":[86,100],"on":[87,94,101,113],"ST":[88,115],"MuST-C":[89],"English-German,":[90],"WER":[91],"11.61%":[93],"ASR":[95,122],"TEDLium":[96],"v3,":[97],"23.35":[98],"MT":[102],"WMT\u201915":[103],"English-German":[104],"task.":[105],"sets":[107],"new":[109],"state-of-the-art":[110],"(SOTA)":[112],"outperforming":[118],"existing":[120],"end-to-end":[121],"systems.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
