{"id":"https://openalex.org/W4390778590","doi":"https://doi.org/10.1109/lsp.2024.3353039","title":"Transformer-Based End-to-End Speech Translation With Rotary Position Embedding","display_name":"Transformer-Based End-to-End Speech Translation With Rotary Position Embedding","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390778590","doi":"https://doi.org/10.1109/lsp.2024.3353039"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3353039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3353039","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/A5100764678","display_name":"Xueqing Li","orcid":"https://orcid.org/0009-0000-9835-1682"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqing Li","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0009-0000-9835-1682","affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101523840","display_name":"Shengqiang Li","orcid":"https://orcid.org/0000-0002-0837-6366"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengqiang Li","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0001-7694-193X","affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054558832","display_name":"Susanto Rahardja","orcid":"https://orcid.org/0000-0003-0831-6934"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Susanto Rahardja","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0003-0831-6934","affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9711,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94052576,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"371","last_page":"375"},"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":0.9994999766349792,"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":0.9975000023841858,"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/embedding","display_name":"Embedding","score":0.8120561838150024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.705113410949707},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6738545298576355},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5392684936523438},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5273248553276062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48298847675323486},{"id":"https://openalex.org/keywords/rope","display_name":"Rope","score":0.4390407204627991},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4327070713043213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4211714267730713},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30421969294548035},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1493019163608551},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0965011715888977}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8120561838150024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705113410949707},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6738545298576355},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5392684936523438},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5273248553276062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48298847675323486},{"id":"https://openalex.org/C162269090","wikidata":"https://www.wikidata.org/wiki/Q1156047","display_name":"Rope","level":2,"score":0.4390407204627991},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4327070713043213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4211714267730713},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30421969294548035},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1493019163608551},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0965011715888977},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3353039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3353039","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":[{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G5057566376","display_name":null,"funder_award_id":"62176211","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1549410849","https://openalex.org/W2582956876","https://openalex.org/W2605131327","https://openalex.org/W2904571617","https://openalex.org/W2963532001","https://openalex.org/W2964161387","https://openalex.org/W2973048981","https://openalex.org/W2994772196","https://openalex.org/W3034625919","https://openalex.org/W3037217258","https://openalex.org/W3097030750","https://openalex.org/W3105669983","https://openalex.org/W3132607382","https://openalex.org/W3198959024","https://openalex.org/W4205879700","https://openalex.org/W4221163209","https://openalex.org/W4225739182","https://openalex.org/W4226212120","https://openalex.org/W4256701369","https://openalex.org/W4287824654","https://openalex.org/W4288089799","https://openalex.org/W4297841598","https://openalex.org/W4300558631","https://openalex.org/W4385893869","https://openalex.org/W4388979610","https://openalex.org/W6739901393","https://openalex.org/W6769627184","https://openalex.org/W6770980983","https://openalex.org/W6771497439","https://openalex.org/W6771917389","https://openalex.org/W6779902714","https://openalex.org/W6784050962","https://openalex.org/W6839435366","https://openalex.org/W6898634591"],"related_works":["https://openalex.org/W2382190654","https://openalex.org/W2041034200","https://openalex.org/W2373129217","https://openalex.org/W1924903628","https://openalex.org/W2375717371","https://openalex.org/W4390286213","https://openalex.org/W2372453219","https://openalex.org/W3173532932","https://openalex.org/W2393872772","https://openalex.org/W1982975944"],"abstract_inverted_index":{"Recently,":[0],"many":[1],"Transformer-based":[2,87],"models":[3,25],"have":[4],"been":[5],"applied":[6],"to":[7,15,70],"end-to-end":[8],"speech":[9,48,88,150,159],"translation":[10,49,89,151,160,183],"because":[11],"of":[12,31,114,121,137,171],"their":[13],"capability":[14],"model":[16],"global":[17],"dependencies.":[18],"Position":[19],"embedding":[20,44,85,110,133,148,180],"is":[21,129,144],"crucial":[22],"in":[23,47,61,149,181],"Transformer":[24],"as":[26,51],"it":[27],"facilitates":[28],"the":[29,39,52,71,99,112,115,122,126,135,175],"modeling":[30],"dependencies":[32],"between":[33],"elements":[34],"at":[35],"various":[36],"positions":[37],"within":[38],"input":[40,100],"sequence.":[41],"Most":[42],"position":[43,56,84,95,109,132,141,147,179],"methods":[45],"employed":[46],"such":[50],"absolute":[53,94,138],"and":[54,105,139],"relative":[55,63,108,140],"embedding,":[57,142],"often":[58],"encounter":[59],"challenges":[60],"leveraging":[62],"positional":[64],"information":[65,96],"or":[66],"adding":[67],"computational":[68],"burden":[69],"model.":[72],"In":[73],"this":[74],"letter,":[75],"we":[76],"introduce":[77],"a":[78,157],"novel":[79],"approach":[80],"by":[81,97],"incorporating":[82],"rotary":[83,131,178],"into":[86],"(RoPE-ST).":[90],"RoPE-ST":[91,166],"first":[92],"adds":[93],"multiplying":[98],"vector":[101],"with":[102],"rotation":[103],"matrices,":[104],"then":[106],"implements":[107],"through":[111],"dot-product":[113],"self-attention":[116],"mechanism.":[117],"The":[118],"main":[119],"advantage":[120],"proposed":[123],"method":[124,128,176],"over":[125,174],"original":[127],"that":[130,165],"combines":[134],"benefits":[136],"which":[143],"suited":[145],"for":[146],"tasks.":[152],"We":[153],"conduct":[154],"experiments":[155],"on":[156],"multilingual":[158],"corpus":[161],"MuST-C.":[162],"Results":[163],"show":[164],"achieves":[167],"an":[168],"average":[169],"improvement":[170],"2.91":[172],"BLEU":[173],"without":[177],"eight":[182],"directions.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
