{"id":"https://openalex.org/W4412945306","doi":"https://doi.org/10.18653/v1/2025.acl-long.681","title":"SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning","display_name":"SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945306","doi":"https://doi.org/10.18653/v1/2025.acl-long.681"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.681","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.681","pdf_url":"https://aclanthology.org/2025.acl-long.681.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.681.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101330599","display_name":"Prabhat Pandey","orcid":"https://orcid.org/0000-0003-0267-751X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prabhat Pandey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076547892","display_name":"Rupak Vignesh Swaminathan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rupak Vignesh Swaminathan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103008705","display_name":"K V Vijay Girish","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K V Vijay Girish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026220576","display_name":"Arunasish Sen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arunasish Sen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010585796","display_name":"Jian Feng Xie","orcid":"https://orcid.org/0000-0002-6988-1630"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian. Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023708721","display_name":"Grant P. Strimel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grant Strimel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056885986","display_name":"Andreas Schwarz","orcid":"https://orcid.org/0000-0002-3883-4989"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Schwarz","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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13921","last_page":"13942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9732000231742859,"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":0.9607999920845032,"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/computer-science","display_name":"Computer science","score":0.7198881506919861},{"id":"https://openalex.org/keywords/scale-invariant-feature-transform","display_name":"Scale-invariant feature transform","score":0.7187592387199402},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6522156596183777},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5840395092964172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5579730272293091},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4602910280227661},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.20874527096748352},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0535968542098999}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7198881506919861},{"id":"https://openalex.org/C61265191","wikidata":"https://www.wikidata.org/wiki/Q767770","display_name":"Scale-invariant feature transform","level":3,"score":0.7187592387199402},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6522156596183777},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5840395092964172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579730272293091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4602910280227661},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.20874527096748352},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0535968542098999},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.681","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.681","pdf_url":"https://aclanthology.org/2025.acl-long.681.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.681","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.681","pdf_url":"https://aclanthology.org/2025.acl-long.681.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945306.pdf","grobid_xml":"https://content.openalex.org/works/W4412945306.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3034955165","https://openalex.org/W2094920358","https://openalex.org/W2041448692","https://openalex.org/W2247121321","https://openalex.org/W2391926582","https://openalex.org/W2087391438","https://openalex.org/W1966831329","https://openalex.org/W2316074893","https://openalex.org/W2020188645","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Prabhat":[0],"Pandey,":[1],"Rupak":[2],"Vignesh":[3],"Swaminathan,":[4],"K":[5],"V":[6],"Vijay":[7],"Girish,":[8],"Arunasish":[9],"Sen,":[10],"Jian.":[11],"Xie,":[12],"Grant":[13],"Strimel,":[14],"Andreas":[15],"Schwarz.":[16],"Proceedings":[17],"of":[18,23],"the":[19,24],"63rd":[20],"Annual":[21],"Meeting":[22],"Association":[25],"for":[26],"Computational":[27],"Linguistics":[28],"(Volume":[29],"1:":[30],"Long":[31],"Papers).":[32],"2025.":[33]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
