{"id":"https://openalex.org/W7126431275","doi":"https://doi.org/10.18653/v1/2022.wmt-1.13","title":"Don\u2019t Discard Fixed-Window Audio Segmentation in Speech-to-Text Translation","display_name":"Don\u2019t Discard Fixed-Window Audio Segmentation in Speech-to-Text Translation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W7126431275","doi":"https://doi.org/10.18653/v1/2022.wmt-1.13"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2022.wmt-1.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wmt-1.13","pdf_url":"https://aclanthology.org/2022.wmt-1.13.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 Seventh Conference on Machine Translation (WMT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2022.wmt-1.13.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086632463","display_name":"Chantal Amrhein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chantal Amrhein","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124594455","display_name":"Barry Haddow","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barry Haddow","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"203","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5264999866485596,"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":0.5264999866485596,"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/T10860","display_name":"Speech and Audio Processing","score":0.20280000567436218,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.0706000030040741,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/segmentation","display_name":"Segmentation","score":0.4959000051021576},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.41429999470710754},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.31290000677108765},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2809000015258789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869999766349792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5591999888420105},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4959000051021576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4203000068664551},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.41429999470710754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.wmt-1.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wmt-1.13","pdf_url":"https://aclanthology.org/2022.wmt-1.13.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 Seventh Conference on Machine Translation (WMT)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.wmt-1.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wmt-1.13","pdf_url":"https://aclanthology.org/2022.wmt-1.13.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 Seventh Conference on Machine Translation (WMT)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6031099476","display_name":"European Live Translator","funder_award_id":"825460","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6048348966","display_name":"Multi-Task Learning with Multilingual Resources for Better Natural Language Understanding","funder_award_id":"176727","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G6458387989","display_name":"Global Under-Resourced MEedia Translation","funder_award_id":"825299","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320323874","display_name":"Universit\u00e4t Z\u00fcrich","ror":"https://ror.org/02crff812"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126431275.pdf","grobid_xml":"https://content.openalex.org/works/W7126431275.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"For":[0],"real-life":[1],"applications,":[2],"it":[3],"is":[4,36],"crucial":[5],"that":[6,85],"endto-end":[7],"spoken":[8,23],"language":[9,24,82],"translation":[10,73],"models":[11,27],"perform":[12,92],"well":[13,94],"on":[14,19,72,79],"continuous":[15],"audio,":[16],"without":[17],"relying":[18],"human-supplied":[20],"segmentation.For":[21],"online":[22,67],"translation,":[25],"where":[26],"need":[28],"to":[29],"start":[30],"translating":[31],"before":[32],"the":[33,43,96],"full":[34],"utterance":[35],"spoken,":[37],"most":[38],"previous":[39],"work":[40],"has":[41],"ignored":[42],"segmentation":[44,57,61,90],"problem.In":[45],"this":[46],"paper,":[47],"we":[48],"compare":[49],"various":[50],"methods":[51],"for":[52],"improving":[53],"models'":[54],"robustness":[55],"towards":[56],"errors":[58],"and":[59,66,69,76],"different":[60,81],"strategies":[62],"in":[63],"both":[64],"offline":[65],"settings":[68],"report":[70],"results":[71],"quality,":[74],"flicker":[75],"delay.Our":[77],"findings":[78],"five":[80],"pairs":[83],"show":[84],"a":[86],"simple":[87],"fixed-window":[88],"audio":[89],"can":[91],"surprisingly":[93],"given":[95],"right":[97],"conditions.":[98],"1":[99]},"counts_by_year":[],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2026-02-02T00:00:00"}