{"id":"https://openalex.org/W4402669746","doi":"https://doi.org/10.18653/v1/2024.iwslt-1.3","title":"NICT\u2019s Cascaded and End-To-End Speech Translation Systems using Whisper and IndicTrans2 for the Indic Task","display_name":"NICT\u2019s Cascaded and End-To-End Speech Translation Systems using Whisper and IndicTrans2 for the Indic Task","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402669746","doi":"https://doi.org/10.18653/v1/2024.iwslt-1.3"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.iwslt-1.3","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.iwslt-1.3","pdf_url":"https://aclanthology.org/2024.iwslt-1.3.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 21st International Conference on Spoken Language Translation (IWSLT 2024)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.iwslt-1.3.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077362985","display_name":"Raj Dabre","orcid":"https://orcid.org/0000-0003-0664-3421"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Raj Dabre","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT) Hikaridai 3-5 , Seika-cho , Soraku-gun , Kyoto , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT) Hikaridai 3-5 , Seika-cho , Soraku-gun , Kyoto , Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033608663","display_name":"Haiyue Song","orcid":"https://orcid.org/0000-0003-1159-0918"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haiyue Song","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT) Hikaridai 3-5 , Seika-cho , Soraku-gun , Kyoto , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT) Hikaridai 3-5 , Seika-cho , Soraku-gun , Kyoto , Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9103000164031982,"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":0.9103000164031982,"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/speech-translation","display_name":"Speech translation","score":0.775191068649292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7416590452194214},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7204673290252686},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.583360493183136},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4207225441932678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2312425673007965},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.21449628472328186},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12034410238265991},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08878549933433533}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.775191068649292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7416590452194214},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7204673290252686},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.583360493183136},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4207225441932678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2312425673007965},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.21449628472328186},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12034410238265991},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08878549933433533}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.iwslt-1.3","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.iwslt-1.3","pdf_url":"https://aclanthology.org/2024.iwslt-1.3.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 21st International Conference on Spoken Language Translation (IWSLT 2024)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.iwslt-1.3","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.iwslt-1.3","pdf_url":"https://aclanthology.org/2024.iwslt-1.3.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 21st International Conference on Spoken Language Translation (IWSLT 2024)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402669746.pdf","grobid_xml":"https://content.openalex.org/works/W4402669746.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2990025607","https://openalex.org/W3045103338","https://openalex.org/W3007142233","https://openalex.org/W2111658398","https://openalex.org/W4399356803","https://openalex.org/W3177132412","https://openalex.org/W3198731777"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,7,87,101,111,117,127,134,142,146,151],"NICT's":[4],"submission":[5],"for":[6,55,62,74],"IWSLT":[8],"2024":[9],"Indic":[10,95],"track,":[11],"focusing":[12],"on":[13],"three":[14],"speech-to-text":[15],"(ST)":[16],"translation":[17,28,45,152],"directions:":[18],"English":[19,103],"to":[20,26,90,109,145],"Hindi,":[21],"Bengali,":[22],"and":[23,42,57],"Tamil.We":[24],"aim":[25],"enhance":[27],"quality":[29,153],"in":[30,94],"this":[31],"low-resource":[32],"scenario":[33],"by":[34,154],"integrating":[35],"state-ofthe-art":[36],"pre-trained":[37],"automated":[38],"speech":[39,104],"recognition":[40],"(ASR)":[41],"text-to-text":[43],"machine":[44],"(MT)":[46],"models.Our":[47],"cascade":[48],"system":[49,68,119],"incorporates":[50],"a":[51,71,121],"Whisper":[52,72,112],"model":[53,60,73,89,144,149],"fine-tuned":[54,61],"ASR":[56],"an":[58,66,81],"IndicTrans2":[59,82,88],"MT.Additionally,":[63],"we":[64],"propose":[65],"end-to-end":[67,128,147],"that":[69,116,137],"combines":[70],"speech-totext":[75],"conversion":[76],"with":[77,100],"knowledge":[78,139],"distilled":[79],"from":[80,141],"MT":[83],"model.We":[84],"first":[85],"fine-tune":[86,110],"generate":[91],"pseudo":[92,97],"data":[93],"languages.This":[96],"data,":[98,105],"along":[99],"original":[102],"is":[106],"then":[107],"used":[108],"model.Experimental":[113],"results":[114],"show":[115],"cascaded":[118],"achieved":[120],"BLEU":[122],"score":[123],"of":[124],"51.0,":[125],"outperforming":[126],"model,":[129],"which":[130],"scored":[131],"19.1":[132],"BLEU.Moreover,":[133],"analysis":[135],"indicates":[136],"applying":[138],"distillation":[140],"In-dicTrans2":[143],"ST":[148],"improves":[150],"about":[155],"0.7":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}