{"id":"https://openalex.org/W4395069496","doi":"https://doi.org/10.1109/lsp.2024.3393353","title":"Improving Speech Translation by Understanding the Speech From Latent Code","display_name":"Improving Speech Translation by Understanding the Speech From Latent Code","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4395069496","doi":"https://doi.org/10.1109/lsp.2024.3393353"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3393353","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lsp.2024.3393353","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5024433209","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0001-8852-6311"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["School of the Information Engineering University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8852-6311","affiliations":[{"raw_affiliation_string":"School of the Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024319575","display_name":"Nianwen Si","orcid":"https://orcid.org/0000-0003-4619-4325"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nianwen Si","raw_affiliation_strings":["School of the Information Engineering University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4619-4325","affiliations":[{"raw_affiliation_string":"School of the Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635256","display_name":"Wenlin Zhang","orcid":"https://orcid.org/0000-0002-6842-9722"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenlin Zhang","raw_affiliation_strings":["School of the Information Engineering University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6842-9722","affiliations":[{"raw_affiliation_string":"School of the Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074428051","display_name":"Xukui Yang","orcid":"https://orcid.org/0000-0002-7989-7089"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xukui Yang","raw_affiliation_strings":["School of the Information Engineering University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7989-7089","affiliations":[{"raw_affiliation_string":"School of the Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001488518","display_name":"Dan Qu","orcid":"https://orcid.org/0000-0001-9917-7794"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Qu","raw_affiliation_strings":["School of the Information Engineering University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9917-7794","affiliations":[{"raw_affiliation_string":"School of the Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I169689159"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04145566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"1259","last_page":"1263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","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/T12031","display_name":"Speech and dialogue systems","score":0.9984999895095825,"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":0.7490719556808472},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6921687126159668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6569381356239319},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5456216931343079},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44738271832466125},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4369221031665802},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4308202564716339},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4169260263442993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3752165138721466},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.27714940905570984},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09475383162498474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490719556808472},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6921687126159668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6569381356239319},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5456216931343079},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44738271832466125},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4369221031665802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4308202564716339},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4169260263442993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3752165138721466},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.27714940905570984},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09475383162498474},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3393353","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lsp.2024.3393353","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2727895085","display_name":null,"funder_award_id":"232300421240","funder_id":"https://openalex.org/F4320323845","funder_display_name":"Natural Science Foundation of Henan Province"},{"id":"https://openalex.org/G7804056170","display_name":null,"funder_award_id":"62171470","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"},{"id":"https://openalex.org/F4320323845","display_name":"Natural Science Foundation of Henan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2101105183","https://openalex.org/W2113106066","https://openalex.org/W2605131327","https://openalex.org/W2936969148","https://openalex.org/W2963223306","https://openalex.org/W2963713328","https://openalex.org/W2970646865","https://openalex.org/W2972584841","https://openalex.org/W3034992210","https://openalex.org/W3097301532","https://openalex.org/W3105669983","https://openalex.org/W3113908264","https://openalex.org/W3153583341","https://openalex.org/W3196833881","https://openalex.org/W4224988050","https://openalex.org/W4225318329","https://openalex.org/W4226212120","https://openalex.org/W4287890956","https://openalex.org/W4300558631","https://openalex.org/W4322577229","https://openalex.org/W4372265871","https://openalex.org/W4385245566","https://openalex.org/W4385570154","https://openalex.org/W4385570757","https://openalex.org/W4385571004","https://openalex.org/W4385572318","https://openalex.org/W4385573012","https://openalex.org/W6608792757","https://openalex.org/W6785130102","https://openalex.org/W6810118069","https://openalex.org/W6849230176","https://openalex.org/W6898634591"],"related_works":["https://openalex.org/W1546240199","https://openalex.org/W193702574","https://openalex.org/W2063862874","https://openalex.org/W2154415461","https://openalex.org/W1923241916","https://openalex.org/W2151365363","https://openalex.org/W2798852438","https://openalex.org/W642007152","https://openalex.org/W254504168","https://openalex.org/W1967664370"],"abstract_inverted_index":{"Due":[0],"to":[1,49,56,65,98],"data":[2],"scarcity":[3],"and":[4,22,35,108,127,157,170],"modal":[5],"complexity,":[6],"the":[7,12,32,36,67,71,75,100,105,125,129,147,161],"semantic":[8,29,59,79,96,122,168],"representations":[9,123],"extracted":[10],"by":[11],"encoder":[13,126],"of":[14,77],"end-to-end":[15],"speech":[16,34,86,107],"translation":[17,45,72,87,134],"(E2E-ST)":[18],"are":[19],"often":[20],"flawed,":[21],"its":[23],"decoder":[24,68,101,130],"will":[25],"further":[26],"produce":[27],"incorrect":[28],"alignment":[30],"between":[31],"source":[33,106],"target":[37,109],"text":[38,110],"based":[39],"on":[40,54,63],"them,":[41],"which":[42,52],"ultimately":[43],"impairs":[44],"performance.":[46],"In":[47],"contrast":[48],"previous":[50],"research,":[51],"focused":[53],"how":[55,64],"extract":[57],"better":[58],"representations,":[60],"we":[61,82],"focus":[62],"assist":[66],"in":[69,74,102,131,175],"performing":[70],"process":[73],"presence":[76],"flawed":[78,120],"representations.":[80],"Specifically,":[81],"propose":[83],"a":[84],"variational":[85],"(VST)":[88],"framework":[89],"that":[90,140,160],"leverages":[91],"latent":[92,114,163],"code":[93,164],"containing":[94],"sentence-level":[95],"information":[97,169],"aid":[99,128],"accurately":[103],"aligning":[104],"semantically.":[111],"By":[112],"leveraging":[113],"code,":[115],"VST":[116,141],"can":[117,142,171],"compensate":[118],"for":[119],"frame-level":[121],"from":[124],"generating":[132],"accurate":[133],"text.":[135],"Our":[136],"experimental":[137],"results":[138],"show":[139],"be":[143],"seamlessly":[144],"integrated":[145],"with":[146],"current":[148],"state-of-the-art":[149],"method,":[150],"achieving":[151],"substantial":[152],"performance":[153],"improvements.":[154],"Further":[155],"analysis":[156],"visualization":[158],"demonstrate":[159],"learned":[162],"indeed":[165],"contain":[166],"rich":[167],"effectively":[172],"rectify":[173],"misalignments":[174],"decoder.":[176]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}