{"id":"https://openalex.org/W4400606403","doi":"https://doi.org/10.1186/s13636-024-00359-1","title":"Adaptive multi-task learning for speech to text translation","display_name":"Adaptive multi-task learning for speech to text translation","publication_year":2024,"publication_date":"2024-07-13","ids":{"openalex":"https://openalex.org/W4400606403","doi":"https://doi.org/10.1186/s13636-024-00359-1"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-024-00359-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00359-1","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00359-1","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00359-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090985486","display_name":"Xin Feng","orcid":"https://orcid.org/0000-0002-8430-1980"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Feng","raw_affiliation_strings":["Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Zhongguancun South Street, Beijing, 100081, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Zhongguancun South Street, Beijing, 100081, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108956725","display_name":"Yue Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhao","raw_affiliation_strings":["Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Zhongguancun South Street, Beijing, 100081, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Zhongguancun South Street, Beijing, 100081, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076268087","display_name":"Wei Zong","orcid":"https://orcid.org/0000-0001-9714-6759"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zong","raw_affiliation_strings":["Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Zhongguancun South Street, Beijing, 100081, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Zhongguancun South Street, Beijing, 100081, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045844800","display_name":"Xiaona Xu","orcid":"https://orcid.org/0000-0001-8715-1618"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaona Xu","raw_affiliation_strings":["Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Zhongguancun South Street, Beijing, 100081, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Zhongguancun South Street, Beijing, 100081, China","institution_ids":["https://openalex.org/I145897649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090985486"],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.8352,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91640388,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2024","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9082428812980652},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.824734628200531},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6262250542640686},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6232651472091675},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6007898449897766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5885369777679443},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5717705488204956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5122458338737488},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.49081310629844666},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4773162305355072},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4544045329093933},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41615256667137146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9082428812980652},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.824734628200531},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6262250542640686},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6232651472091675},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6007898449897766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5885369777679443},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5717705488204956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5122458338737488},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.49081310629844666},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4773162305355072},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4544045329093933},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41615256667137146},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-024-00359-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00359-1","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00359-1","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:60d4d7279c0546b9ac02201d74f4f522","is_oa":true,"landing_page_url":"https://doaj.org/article/60d4d7279c0546b9ac02201d74f4f522","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2024, Iss 1, Pp 1-9 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-024-00359-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00359-1","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00359-1","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G1660390292","display_name":null,"funder_award_id":"61976236","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400606403.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2135708429","https://openalex.org/W2466918907","https://openalex.org/W2963250244","https://openalex.org/W2963430933","https://openalex.org/W2963532001","https://openalex.org/W2963677766","https://openalex.org/W3037542581","https://openalex.org/W3090449556","https://openalex.org/W3102811925","https://openalex.org/W3105825505","https://openalex.org/W3162037819","https://openalex.org/W3163093788","https://openalex.org/W3168212167","https://openalex.org/W3176382501","https://openalex.org/W3176455679","https://openalex.org/W3176711365","https://openalex.org/W3196833881","https://openalex.org/W4206471589","https://openalex.org/W4221163209","https://openalex.org/W4233762729","https://openalex.org/W4234380012","https://openalex.org/W4287890956","https://openalex.org/W4385570154","https://openalex.org/W4385574099","https://openalex.org/W6600424091","https://openalex.org/W6600459194","https://openalex.org/W6743200457"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2084768720","https://openalex.org/W2043010663","https://openalex.org/W4248308508"],"abstract_inverted_index":{"Abstract":[0],"End-to-end":[1],"speech":[2,10,40,68,115,127,159,186],"to":[3,7,48,54,95,116,144,154],"text":[4,15,117,161],"translation":[5,41,52,128,187],"aims":[6],"directly":[8],"translate":[9],"from":[11,130],"one":[12],"language":[13],"into":[14],"in":[16,24,71,111,148],"another,":[17],"posing":[18],"a":[19,75],"challenging":[20,84],"cross-modal":[21],"task":[22],"particularly":[23],"scenarios":[25],"of":[26,67,77,151],"limited":[27],"data.":[28],"Multi-task":[29],"learning":[30,93,113],"serves":[31],"as":[32],"an":[33,90],"effective":[34],"strategy":[35],"for":[36,114],"knowledge":[37],"sharing":[38],"between":[39,58,158,168],"and":[42,60,85,160,163,184],"machine":[43,51],"translation,":[44],"which":[45],"allows":[46],"models":[47,129],"leverage":[49],"extensive":[50],"data":[53,133],"learn":[55,164],"the":[56,65,102,137,149,156,165,178,181],"mapping":[57],"source":[59],"target":[61],"languages,":[62],"thereby":[63],"improving":[64],"performance":[66,179],"translation.":[69,118],"However,":[70],"multi-task":[72,92,98,112],"learning,":[73],"finding":[74],"set":[76],"weights":[78,99],"that":[79,173],"balances":[80],"various":[81],"tasks":[82],"is":[83],"computationally":[86],"expensive.":[87],"We":[88],"proposed":[89,143],"adaptive":[91,109],"method":[94,175],"dynamically":[96],"adjust":[97],"based":[100],"on":[101,180],"proportional":[103],"losses":[104],"incurred":[105],"during":[106],"training,":[107],"enabling":[108],"balance":[110],"Moreover,":[119],"inherent":[120],"representation":[121],"disparities":[122],"across":[123,139],"different":[124,140],"modalities":[125],"impede":[126],"harnessing":[131],"textual":[132],"effectively.":[134],"To":[135],"bridge":[136],"gap":[138],"modalities,":[141],"we":[142],"apply":[145],"optimal":[146],"transport":[147],"input":[150],"end-to-end":[152],"model":[153],"find":[155],"alignment":[157],"sequences":[162],"shared":[166],"representations":[167],"them.":[169],"Experimental":[170],"results":[171],"show":[172],"our":[174],"effectively":[176],"improved":[177],"Tibetan-Chinese,":[182],"English-German,":[183],"English-French":[185],"datasets.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
