{"id":"https://openalex.org/W4391021669","doi":"https://doi.org/10.1109/asru57964.2023.10389709","title":"Improving Stability in Simultaneous Speech Translation: A Revision-Controllable Decoding Approach","display_name":"Improving Stability in Simultaneous Speech Translation: A Revision-Controllable Decoding Approach","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021669","doi":"https://doi.org/10.1109/asru57964.2023.10389709"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5034556928","display_name":"Junkun Chen","orcid":"https://orcid.org/0000-0003-0193-238X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junkun Chen","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112111485","display_name":"Jian Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jian Xue","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peidong Wang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875418","display_name":"Jing Pan","orcid":"https://orcid.org/0000-0002-5178-2247"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jing Pan","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50456317,"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":"7"},"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/T12031","display_name":"Speech and dialogue systems","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/T10201","display_name":"Speech Recognition and Synthesis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.8255660533905029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7776153087615967},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.668708086013794},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6433356404304504},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6087114810943604},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.575238049030304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5559577345848083},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5519890785217285},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5333013534545898},{"id":"https://openalex.org/keywords/flicker","display_name":"Flicker","score":0.465468168258667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4517516493797302},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32882028818130493},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27388209104537964},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.263869971036911},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09482958912849426},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.0738411545753479},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06234103441238403}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8255660533905029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7776153087615967},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.668708086013794},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6433356404304504},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6087114810943604},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.575238049030304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5559577345848083},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5519890785217285},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5333013534545898},{"id":"https://openalex.org/C19743564","wikidata":"https://www.wikidata.org/wiki/Q25378119","display_name":"Flicker","level":2,"score":0.465468168258667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4517516493797302},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32882028818130493},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27388209104537964},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.263869971036911},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09482958912849426},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0738411545753479},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06234103441238403},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1991646969","https://openalex.org/W2064675550","https://openalex.org/W2157817599","https://openalex.org/W2566564022","https://openalex.org/W2936969148","https://openalex.org/W2951456627","https://openalex.org/W2963532001","https://openalex.org/W2970084653","https://openalex.org/W2981022124","https://openalex.org/W3015583403","https://openalex.org/W3016010032","https://openalex.org/W3034586846","https://openalex.org/W3105422997","https://openalex.org/W3132972333","https://openalex.org/W3161873870","https://openalex.org/W3174032041","https://openalex.org/W3196509775","https://openalex.org/W3199917453","https://openalex.org/W3211848854","https://openalex.org/W4224137820","https://openalex.org/W4288088457","https://openalex.org/W4319862688","https://openalex.org/W4385571513","https://openalex.org/W4391021779","https://openalex.org/W4391021781","https://openalex.org/W6638749077","https://openalex.org/W6687218720","https://openalex.org/W6757817989","https://openalex.org/W6769806307","https://openalex.org/W6846175339","https://openalex.org/W6854771245"],"related_works":["https://openalex.org/W2461212857","https://openalex.org/W2393542839","https://openalex.org/W1968167504","https://openalex.org/W2608689891","https://openalex.org/W2594237268","https://openalex.org/W2081192961","https://openalex.org/W2136056355","https://openalex.org/W2007560172","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"Simultaneous":[0],"Speech-to-Text":[1],"translation":[2,24,106],"serves":[3],"a":[4,26,41,75],"critical":[5],"role":[6],"in":[7,14,19,22,30,78],"real-time":[8],"crosslingual":[9],"communication.":[10],"Despite":[11],"the":[12,23,31,58,83,92,98,105],"advancements":[13],"recent":[15],"years,":[16],"challenges":[17],"remain":[18],"achieving":[20],"stability":[21,100],"process,":[25],"concern":[27],"primarily":[28],"manifested":[29],"flickering":[32,79],"of":[33],"partial":[34],"results.":[35],"In":[36],"this":[37,48],"paper,":[38],"we":[39],"propose":[40],"novel":[42],"revision-controllable":[43],"method":[44,51,94],"designed":[45],"to":[46,63,69,74,85],"address":[47],"issue.":[49],"Our":[50],"introduces":[52],"an":[53],"allowed":[54],"revision":[55],"window":[56],"within":[57],"beam":[59],"search":[60],"pruning":[61],"process":[62],"screen":[64],"out":[65],"candidate":[66],"translations":[67],"likely":[68],"cause":[70],"extensive":[71],"revisions,":[72],"leading":[73],"substantial":[76],"reduction":[77],"and,":[80],"crucially,":[81],"providing":[82],"capability":[84],"completely":[86],"eliminate":[87],"flickering.":[88],"The":[89],"experiments":[90],"demonstrate":[91],"proposed":[93],"can":[95],"significantly":[96],"improve":[97],"decoding":[99],"without":[101],"compromising":[102],"substantially":[103],"on":[104],"quality.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}