{"id":"https://openalex.org/W4412944375","doi":"https://doi.org/10.18653/v1/2025.iwslt-1.31","title":"CMU\u2019s IWSLT 2025 Simultaneous Speech Translation System","display_name":"CMU\u2019s IWSLT 2025 Simultaneous Speech Translation System","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944375","doi":"https://doi.org/10.18653/v1/2025.iwslt-1.31"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.iwslt-1.31","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.iwslt-1.31","pdf_url":"https://aclanthology.org/2025.iwslt-1.31.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.iwslt-1.31.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057636712","display_name":"Siqi Ouyang","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":"Siqi Ouyang","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101225200","display_name":"Xi Xu","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":"Xi Xu","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440407","display_name":"Lei Li","orcid":"https://orcid.org/0000-0003-3095-9776"},"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":"Lei Li","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University , USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"309","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8119000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8119000196456909,"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":0.7724999785423279,"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":0.7447803616523743},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7433106899261475},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6421776413917542},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5840638279914856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3671156167984009},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3660007119178772},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.30916446447372437},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.04310774803161621}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7447803616523743},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7433106899261475},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6421776413917542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5840638279914856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3671156167984009},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3660007119178772},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.30916446447372437},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.04310774803161621},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.iwslt-1.31","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.iwslt-1.31","pdf_url":"https://aclanthology.org/2025.iwslt-1.31.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.iwslt-1.31","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.iwslt-1.31","pdf_url":"https://aclanthology.org/2025.iwslt-1.31.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944375.pdf","grobid_xml":"https://content.openalex.org/works/W4412944375.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4387725353"],"related_works":["https://openalex.org/W2775554247","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613","https://openalex.org/W123774389"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"CMU's":[3],"submission":[4],"to":[5],"the":[6,42,44,93],"IWSLT":[7],"2025":[8],"Simultaneous":[9],"Speech":[10],"Translation":[11],"(SST)":[12],"task":[13],"for":[14,84,89],"translating":[15],"unsegmented":[16],"English":[17],"speech":[18,37,54],"into":[19],"Chinese":[20],"and":[21,41,60,86,103,106,111],"German":[22],"text":[23],"in":[24],"a":[25,32,47,72],"streaming":[26],"manner.Our":[27],"end-to-end":[28],"speechto-text":[29],"system":[30,80],"integrates":[31],"chunkwise":[33],"causal":[34],"Wav2Vec":[35],"2.0":[36],"encoder,":[38],"an":[39],"adapter,":[40],"Qwen2.5-7B-Instructas":[43],"decoder.We":[45],"use":[46],"two-stage":[48],"simultaneous":[49],"training":[50],"procedure":[51],"on":[52,92],"robust":[53],"segments":[55],"curated":[56],"from":[57],"LibriSpeech,":[58],"CommonVoice,":[59],"VoxPopuli":[61],"datasets,":[62],"utilizing":[63],"standard":[64],"cross-entropy":[65],"loss.Our":[66],"model":[67],"supports":[68],"adjustable":[69],"latency":[70,74],"through":[71],"configurable":[73],"multiplier.Experimental":[75],"results":[76],"demonstrate":[77],"that":[78],"our":[79],"achieves":[81],"44.3":[82],"BLEU":[83,88],"English-to-Chinese":[85],"25.1":[87],"English-to-German":[90],"translations":[91],"ACL60/60":[94],"development":[95],"set,":[96],"with":[97],"computation-aware":[98],"latencies":[99,108],"of":[100,109],"2.7":[101],"seconds":[102],"2.3":[104],"seconds,":[105,113],"theoretical":[107],"2.2":[110],"1.7":[112],"respectively.":[114]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
