{"id":"https://openalex.org/W4402670495","doi":"https://doi.org/10.18653/v1/2024.iwslt-1.17","title":"QUESPA Submission for the IWSLT 2024 Dialectal and Low-resource Speech Translation Task","display_name":"QUESPA Submission for the IWSLT 2024 Dialectal and Low-resource Speech Translation Task","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402670495","doi":"https://doi.org/10.18653/v1/2024.iwslt-1.17"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.iwslt-1.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.iwslt-1.17","pdf_url":"https://aclanthology.org/2024.iwslt-1.17.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-1.17.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050439418","display_name":"John E. Ortega","orcid":"https://orcid.org/0000-0002-2328-3205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John E. Ortega","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111333826","display_name":"Rodolfo Joel Zevallos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rodolfo Joel Zevallos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023958796","display_name":"Ibrahim Said Ahmad","orcid":"https://orcid.org/0000-0001-9514-1807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ibrahim Said Ahmad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055644612","display_name":"William Chen","orcid":"https://orcid.org/0000-0001-8924-5853"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Chen","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"125","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9897000193595886,"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":0.9897000193595886,"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":0.934499979019165,"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":0.9180999994277954,"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":0.7700678706169128},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7160789966583252},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.648169755935669},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5953949093818665},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5635344386100769},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5190846920013428},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4693625569343567},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.46605026721954346},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42342615127563477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.402959406375885},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08592179417610168}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700678706169128},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7160789966583252},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.648169755935669},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5953949093818665},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5635344386100769},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5190846920013428},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4693625569343567},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.46605026721954346},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42342615127563477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.402959406375885},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08592179417610168},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.iwslt-1.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.iwslt-1.17","pdf_url":"https://aclanthology.org/2024.iwslt-1.17.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-1.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.iwslt-1.17","pdf_url":"https://aclanthology.org/2024.iwslt-1.17.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402670495.pdf","grobid_xml":"https://content.openalex.org/works/W4402670495.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W4301342010","https://openalex.org/W158465921","https://openalex.org/W3151736118","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W2293738010","https://openalex.org/W4360995948"],"abstract_inverted_index":{"This":[0],"article":[1],"describes":[2],"the":[3,11,19,36,50,89,94,107,146,161,169,182,200,224],"QUESPA":[4],"team":[5],"speech":[6,28,229],"translation":[7],"(ST)":[8],"submissions":[9,203],"for":[10,156,228],"Quechua":[12],"to":[13,49,70,117,127,137,194],"Spanish":[14],"(QUE-SPA)":[15],"track":[16],"featured":[17],"in":[18,35,176],"Evaluation":[20],"Campaign":[21],"of":[22,75,83,163,172,184,212,215,226],"IWSLT":[23,51],"2024:":[24],"dialectal":[25],"and":[26,39,54,106,160,187,206,217,223],"low-resource":[27],"translation.Two":[29],"main":[30],"submission":[31,120],"types":[32],"were":[33,68,97,109,135],"supported":[34],"campaign:":[37],"constrained":[38,80,205],"unconstrained.This":[40],"is":[41],"our":[42,46,77],"second":[43],"year":[44,144],"submitting":[45],"ST":[47,85,157,178],"systems":[48,74],"shared":[52],"task":[53,148],"we":[55,58,67,134,198],"feel":[56],"that":[57],"have":[59],"achieved":[60],"novel":[61],"performance,":[62],"surpassing":[63],"last":[64,118,143],"year's":[65,119],"submissions.Again,":[66],"able":[69,136],"submit":[71],"six":[72],"total":[73],"which":[76,209],"best":[78],"(primary)":[79],"system":[81,114],"consisted":[82],"an":[84],"model":[86,155,175],"based":[87],"on":[88,145,168,220],"Fairseq":[90],"S2T":[91],"framework":[92],"where":[93],"audio":[95],"representations":[96],"created":[98],"using":[99,111,149],"log":[100],"mel-scale":[101],"filter":[102],"banks":[103],"as":[104],"features":[105],"translations":[108],"performed":[110],"a":[112,150,177,188],"transformer.The":[113],"was":[115],"similar":[116],"with":[121,181],"slight":[122],"configuration":[123,218],"changes,":[124],"allowing":[125],"us":[126,193],"achieve":[128,138,195],"slightly":[129],"higher":[130],"performance":[131,141],"(2":[132,204],"BLEU).Contrastingly,":[133],"much":[139],"better":[140],"than":[142],"unconstrained":[147],"larger":[151],"pre-trained":[152],"language":[153],"(PLM)":[154],"(without":[158],"cascading)":[159],"inclusion":[162,225],"parallel":[164],"QUE-SPA":[165],"data":[166,186,189],"found":[167],"internet.The":[170],"fine-tuning":[171],"Microsoft's":[173],"SpeechT5":[174],"setting":[179],"along":[180],"addition":[183],"new":[185],"augmentation":[190],"technique":[191],"allowed":[192],"19.7":[196],"BLEU.Additionally,":[197],"present":[199],"other":[201],"four":[202],"2":[207],"unconstrained)":[208],"are":[210],"part":[211],"additional":[213],"efforts":[214],"hyper-parameter":[216],"tuning":[219],"existent":[221],"models":[222],"Whisper":[227],"recognition.":[230]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
