{"id":"https://openalex.org/W4392903654","doi":"https://doi.org/10.1109/icassp48485.2024.10446102","title":"Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization","display_name":"Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903654","doi":"https://doi.org/10.1109/icassp48485.2024.10446102"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5014592910","display_name":"Amir Hussein","orcid":"https://orcid.org/0000-0002-0820-4062"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Hussein","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021201726","display_name":"Brian Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Yan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013793053","display_name":"Antonios Anastasopoulos","orcid":"https://orcid.org/0000-0002-8544-246X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonios Anastasopoulos","raw_affiliation_strings":["George Mason University,USA","George Mason University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University,USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"George Mason University, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11971","last_page":"11975"},"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":0.9997000098228455,"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":0.998199999332428,"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":0.8571809530258179},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6377043724060059},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.601201057434082},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5811747312545776},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5285688042640686},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5057153701782227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45190539956092834},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.44552671909332275},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4436802268028259},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4145594835281372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8571809530258179},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6377043724060059},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.601201057434082},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5811747312545776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5285688042640686},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5057153701782227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45190539956092834},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.44552671909332275},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4436802268028259},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4145594835281372},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1841959837","https://openalex.org/W2103123519","https://openalex.org/W2135708429","https://openalex.org/W2606531491","https://openalex.org/W2741363662","https://openalex.org/W2759173152","https://openalex.org/W2771976988","https://openalex.org/W2799051177","https://openalex.org/W2891534142","https://openalex.org/W2936774411","https://openalex.org/W2946764509","https://openalex.org/W2952446148","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2964093087","https://openalex.org/W2972430654","https://openalex.org/W3015186746","https://openalex.org/W3035520602","https://openalex.org/W3037465386","https://openalex.org/W3037469336","https://openalex.org/W3037542581","https://openalex.org/W3094821064","https://openalex.org/W3097777922","https://openalex.org/W3172862365","https://openalex.org/W3173657420","https://openalex.org/W3197898596","https://openalex.org/W3200082423","https://openalex.org/W4285269970","https://openalex.org/W4311000453","https://openalex.org/W4372260611","https://openalex.org/W4385245566","https://openalex.org/W4385565440","https://openalex.org/W6691444175","https://openalex.org/W6691814027","https://openalex.org/W6732953234","https://openalex.org/W6736457419","https://openalex.org/W6747942827","https://openalex.org/W6769269733","https://openalex.org/W6775053297","https://openalex.org/W6781389758","https://openalex.org/W6847363464","https://openalex.org/W6931689928"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W4388870064","https://openalex.org/W2004087835"],"abstract_inverted_index":{"Incorporating":[0],"longer":[1],"context":[2,14,30,46,87],"has":[3],"been":[4],"shown":[5],"to":[6,48,51,85],"benefit":[7],"machine":[8],"translation,":[9],"but":[10],"the":[11,52,69],"inclusion":[12],"of":[13,39,54],"in":[15,31,78],"end-to-end":[16],"speech":[17],"translation":[18],"(E2E-ST)":[19],"remains":[20],"under-studied.":[21],"To":[22],"bridge":[23],"this":[24],"gap,":[25],"we":[26,44,75],"introduce":[27],"target":[28],"language":[29],"E2E-ST,":[32],"enhancing":[33],"coherence":[34],"and":[35,56,94],"overcoming":[36],"memory":[37],"constraints":[38],"extended":[40],"audio":[41],"segments.":[42],"Additionally,":[43],"propose":[45],"dropout":[47],"ensure":[49],"robustness":[50],"absence":[53],"context,":[55],"further":[57],"improve":[58],"performance":[59],"by":[60],"adding":[61],"speaker":[62],"information.":[63],"Our":[64],"proposed":[65],"contextual":[66,81],"E2E-ST":[67,72],"outperforms":[68],"isolated":[70],"utterance-based":[71],"approach.":[73],"Lastly,":[74],"demonstrate":[76],"that":[77],"conversational":[79],"speech,":[80],"information":[82],"primarily":[83],"contributes":[84],"capturing":[86],"style,":[88],"as":[89,91],"well":[90],"resolving":[92],"anaphora":[93],"named":[95],"entities.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}