{"id":"https://openalex.org/W4406496878","doi":"https://doi.org/10.1109/slt61566.2024.10832264","title":"Long-Form End-To-End Speech Translation VIA Latent Alignment Segmentation","display_name":"Long-Form End-To-End Speech Translation VIA Latent Alignment Segmentation","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406496878","doi":"https://doi.org/10.1109/slt61566.2024.10832264"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-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/A5019935805","display_name":"Peter Pol\u00e1k","orcid":"https://orcid.org/0000-0003-2332-7666"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Peter Pol\u00e1k","raw_affiliation_strings":["Charles University,Czechia"],"affiliations":[{"raw_affiliation_string":"Charles University,Czechia","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077746237","display_name":"Ond\u0159ej Bojar","orcid":"https://orcid.org/0000-0002-0606-0050"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ond\u0159ej Bojar","raw_affiliation_strings":["Charles University,Czechia"],"affiliations":[{"raw_affiliation_string":"Charles University,Czechia","institution_ids":["https://openalex.org/I21250087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019935805"],"corresponding_institution_ids":["https://openalex.org/I21250087"],"apc_list":null,"apc_paid":null,"fwci":0.63877855,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71097974,"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":"1076","last_page":"1082"},"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":0.9995999932289124,"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":0.996999979019165,"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/translation","display_name":"Translation (biology)","score":0.707856297492981},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.678180456161499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6725898385047913},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.613186776638031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5269715785980225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49111053347587585},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4854357838630676},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47809240221977234},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3011452555656433},{"id":"https://openalex.org/keywords/messenger-rna","display_name":"Messenger RNA","score":0.05771005153656006}],"concepts":[{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.707856297492981},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.678180456161499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6725898385047913},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.613186776638031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5269715785980225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49111053347587585},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4854357838630676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47809240221977234},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3011452555656433},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.05771005153656006},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2089629691","https://openalex.org/W2115210242","https://openalex.org/W2127141656","https://openalex.org/W2129120544","https://openalex.org/W2133564696","https://openalex.org/W2144499799","https://openalex.org/W2163866081","https://openalex.org/W2178770890","https://openalex.org/W2419292002","https://openalex.org/W2512593609","https://openalex.org/W2745785989","https://openalex.org/W2766219058","https://openalex.org/W2883059477","https://openalex.org/W2887005286","https://openalex.org/W2963532001","https://openalex.org/W2963979492","https://openalex.org/W2964078338","https://openalex.org/W2990138404","https://openalex.org/W3015698636","https://openalex.org/W3034625919","https://openalex.org/W3036601975","https://openalex.org/W3037465386","https://openalex.org/W3037625699","https://openalex.org/W3092085609","https://openalex.org/W3101727459","https://openalex.org/W3148654612","https://openalex.org/W3153988736","https://openalex.org/W3156860712","https://openalex.org/W3186200218","https://openalex.org/W3213029956","https://openalex.org/W4224292837","https://openalex.org/W4285158119","https://openalex.org/W4287855189","https://openalex.org/W4297841352","https://openalex.org/W4297841689","https://openalex.org/W4385245566","https://openalex.org/W4385565440","https://openalex.org/W4385570170","https://openalex.org/W4385571023","https://openalex.org/W4385822713","https://openalex.org/W4386566728","https://openalex.org/W6628972281","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6681794868","https://openalex.org/W6684662674","https://openalex.org/W6717306297","https://openalex.org/W6780218876","https://openalex.org/W6794247771","https://openalex.org/W6802354036"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3007142233","https://openalex.org/W2883671469","https://openalex.org/W2990025607","https://openalex.org/W2728761353","https://openalex.org/W3045103338","https://openalex.org/W3177132412","https://openalex.org/W3198731777","https://openalex.org/W4378501567","https://openalex.org/W4385571138"],"abstract_inverted_index":{"Contemporary":[0],"datasets":[1],"provide":[2],"an":[3,53,92],"oracle":[4],"segmentation":[5,16,28,32,43,128],"into":[6,17],"sentences":[7,18],"based":[8],"on":[9],"human-annotated":[10],"transcripts":[11],"and":[12,65,104,114,116],"translations.":[13],"However,":[14],"the":[15,23,35,68,77,80,88,122],"is":[19,87],"not":[20],"available":[21],"in":[22,34],"real":[24],"world.":[25],"Current":[26],"speech":[27,49,55,60,97],"approaches":[29],"offer":[30],"poor":[31],"quality":[33],"low-latency":[36,47],"regime.":[37],"This":[38],"paper":[39],"proposes":[40],"a":[41,46,108],"novel":[42],"approach":[44,124],"for":[45],"end-to-end":[48,95],"translation.":[50],"We":[51],"leverage":[52],"existing":[54],"translation":[56,61],"encoder-decoder":[57],"architecture":[58],"with":[59],"CTC":[62,74],"(ST":[63],"CTC)":[64],"show":[66,120],"that":[67,90,121],"latent":[69],"alignments":[70],"produced":[71],"by":[72],"ST":[73],"can":[75],"guide":[76],"segmentation.":[78],"To":[79],"best":[81],"of":[82,111],"our":[83,85],"knowledge,":[84],"method":[86],"first":[89],"allows":[91],"actual":[93],"long-form":[94],"simultaneous":[96],"translation,":[98],"as":[99],"one":[100],"neural":[101],"model":[102],"translates":[103],"segments":[105],"simultaneously.":[106],"On":[107],"diverse":[109],"set":[110],"language":[112],"pairs":[113],"in-":[115],"out-of-domain":[117],"data,":[118],"we":[119],"proposed":[123],"outperforms":[125],"current":[126],"state-of-the-art":[127],"methods":[129],"at":[130],"no":[131],"additional":[132],"computational":[133],"cost.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-20T08:17:22.645390","created_date":"2025-10-10T00:00:00"}
