{"id":"https://openalex.org/W4412944423","doi":"https://doi.org/10.18653/v1/2025.iwslt-1.36","title":"Instituto de Telecomunica\u00e7\u00f5es at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning","display_name":"Instituto de Telecomunica\u00e7\u00f5es at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944423","doi":"https://doi.org/10.18653/v1/2025.iwslt-1.36"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.iwslt-1.36","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.iwslt-1.36","pdf_url":"https://aclanthology.org/2025.iwslt-1.36.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-1.36.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109379051","display_name":"Giuseppe Attanasio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giuseppe Attanasio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086874545","display_name":"Sonal Sannigrahi","orcid":"https://orcid.org/0009-0004-3092-1502"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sonal Sannigrahi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002087731","display_name":"Ben Peters","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Peters","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051693368","display_name":"Andr\u00e9 F. T. Martins","orcid":"https://orcid.org/0000-0001-8282-625X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Filipe Torres Martins","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":"347","last_page":"353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9460999965667725,"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":0.9460999965667725,"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":0.9067000150680542,"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":0.7572206258773804},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4994032382965088},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4456440508365631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38689035177230835},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38467511534690857}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572206258773804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4994032382965088},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4456440508365631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38689035177230835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38467511534690857}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.iwslt-1.36","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.iwslt-1.36","pdf_url":"https://aclanthology.org/2025.iwslt-1.36.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-1.36","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.iwslt-1.36","pdf_url":"https://aclanthology.org/2025.iwslt-1.36.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G273553189","display_name":null,"funder_award_id":"UID/50008","funder_id":"https://openalex.org/F4320328988","funder_display_name":"Instituto de Telecomunica\u00e7\u00f5es"},{"id":"https://openalex.org/G3850789590","display_name":null,"funder_award_id":"50008","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3884855522","display_name":null,"funder_award_id":"UID/50008","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320328988","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944423.pdf","grobid_xml":"https://content.openalex.org/works/W4412944423.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"Instituto":[3],"de":[4],"Telecomunicaes's":[5],"submission":[6],"to":[7,74,83],"the":[8,21],"IWSLT":[9],"2025":[10],"Shared":[11],"Task":[12],"on":[13,64],"Instruction":[14],"Following":[15],"Speech":[16],"Processing.We":[17],"submit":[18],"results":[19],"for":[20],"Short":[22],"Track,":[23],"i.e.,":[24],"speech":[25,43],"recognition,":[26],"translation,":[27],"and":[28,45,55,72],"spoken":[29],"question":[30],"answering.Our":[31],"model":[32,37,68],"is":[33],"a":[34,40,49,56],"unified":[35],"speech-to-text":[36],"that":[38],"integrates":[39],"pretrained":[41],"continuous":[42],"encoder":[44],"text":[46],"decoder":[47],"through":[48],"first":[50],"phase":[51,58],"of":[52,59],"modality":[53],"alignment":[54],"second":[57],"instruction":[60],"finetuning.Crucially,":[61],"we":[62],"focus":[63],"using":[65],"smallscale":[66],"language":[67],"backbones":[69],"(<":[70],"2B)":[71],"restrict":[73],"high-quality,":[75],"CC-BY":[76],"data":[77,81],"along":[78],"with":[79],"synthetic":[80],"generation":[82],"supplement":[84],"existing":[85],"resources.":[86],"1":[87]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
