{"id":"https://openalex.org/W4408354769","doi":"https://doi.org/10.1109/icassp49660.2025.10887794","title":"A Modular-based Strategy for Mitigating Gradient Conflicts in Simultaneous Speech Translation","display_name":"A Modular-based Strategy for Mitigating Gradient Conflicts in Simultaneous Speech Translation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354769","doi":"https://doi.org/10.1109/icassp49660.2025.10887794"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887794","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":"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/A5100683619","display_name":"Xiaoqian Liu","orcid":"https://orcid.org/0009-0006-1919-6519"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoqian Liu","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100315809","display_name":"Yangfan Du","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangfan Du","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003532221","display_name":"Jianjin Wang","orcid":"https://orcid.org/0000-0002-3416-3399"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjin Wang","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112885302","display_name":"Yuan Ge","orcid":"https://orcid.org/0009-0003-0279-8896"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Ge","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385729","display_name":"Chen Xu","orcid":"https://orcid.org/0000-0002-7238-7254"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Xu","raw_affiliation_strings":["Harbin Engineering University,College of Computer Science and Technology,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015300690","display_name":"Tong Xiao","orcid":"https://orcid.org/0009-0007-7082-6085"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xiao","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001145192","display_name":"Guocheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guocheng Chen","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100370145","display_name":"Jingbo Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Zhu","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100683619"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":2.8076,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89715692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T12031","display_name":"Speech and dialogue systems","score":0.9366000294685364,"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":0.9366000294685364,"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":0.9028000235557556,"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":0.7140886187553406},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.7021430730819702},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6902514696121216},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5168136358261108},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44950070977211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3699343800544739},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3239521384239197},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11548876762390137},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05908626317977905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7140886187553406},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7021430730819702},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6902514696121216},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5168136358261108},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44950070977211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3699343800544739},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3239521384239197},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11548876762390137},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05908626317977905},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887794","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2089629691","https://openalex.org/W2113106066","https://openalex.org/W2121457870","https://openalex.org/W2951456627","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2963779652","https://openalex.org/W2997436923","https://openalex.org/W3092424727","https://openalex.org/W3101727459","https://openalex.org/W3176382501","https://openalex.org/W4223622550","https://openalex.org/W4385571120","https://openalex.org/W4385571138","https://openalex.org/W4401023633","https://openalex.org/W4402112520","https://openalex.org/W6682365476","https://openalex.org/W6744711567","https://openalex.org/W6745410505","https://openalex.org/W6771876938","https://openalex.org/W6780218876","https://openalex.org/W6852354195","https://openalex.org/W6853928898","https://openalex.org/W6898634591"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2378076731","https://openalex.org/W4286888643","https://openalex.org/W4301342010","https://openalex.org/W3210795196","https://openalex.org/W158465921","https://openalex.org/W3151736118","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W123774389"],"abstract_inverted_index":{"Simultaneous":[0],"Speech":[1],"Translation":[2],"(SimulST)":[3],"involves":[4],"generating":[5],"target":[6],"language":[7],"text":[8],"while":[9],"continuously":[10],"processing":[11],"streaming":[12],"speech":[13],"input,":[14],"presenting":[15],"significant":[16],"real-time":[17],"challenges.":[18],"Multi-task":[19],"learning":[20],"is":[21],"often":[22],"employed":[23],"to":[24,58,125],"enhance":[25],"SimulST":[26,97,137],"performance":[27],"but":[28],"introduces":[29],"optimization":[30],"conflicts":[31,78],"between":[32],"primary":[33],"and":[34,56,84,102],"auxiliary":[35],"tasks,":[36],"potentially":[37],"compromising":[38],"overall":[39],"efficiency.":[40],"The":[41],"existing":[42],"model-level":[43],"conflict":[44,127],"resolution":[45],"methods":[46],"are":[47],"not":[48],"well-suited":[49],"for":[50,136],"this":[51],"task":[52],"which":[53],"exacerbates":[54],"inefficiencies":[55],"leads":[57],"high":[59,103],"GPU":[60,118],"memory":[61,119],"consumption.":[62],"To":[63],"address":[64],"these":[65],"challenges,":[66],"we":[67],"propose":[68],"a":[69,80,107,133],"Modular":[70],"Gradient":[71],"Conflict":[72],"Mitigation":[73],"(MGCM)":[74],"strategy":[75],"that":[76,93],"detects":[77],"at":[79],"finer-grained":[81],"modular":[82],"level":[83],"resolves":[85],"them":[86],"utilizing":[87],"gradient":[88],"projection.":[89],"Experimental":[90],"results":[91],"demonstrate":[92],"MGCM":[94,116],"significantly":[95],"improves":[96],"performance,":[98],"particularly":[99],"under":[100],"medium":[101],"latency":[104],"conditions,":[105],"achieving":[106],"0.68":[108],"BLEU":[109],"score":[110],"gain":[111],"in":[112],"offline":[113],"tasks.":[114,138],"Additionally,":[115],"reduces":[117],"consumption":[120],"by":[121],"over":[122],"95%":[123],"compared":[124],"other":[126],"mitigation":[128],"methods,":[129],"establishing":[130],"it":[131],"as":[132],"robust":[134],"solution":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}