{"id":"https://openalex.org/W4406461843","doi":"https://doi.org/10.1109/slt61566.2024.10832199","title":"Improving Rare-Word Recognition of Whisper in Zero-Shot Settings","display_name":"Improving Rare-Word Recognition of Whisper in Zero-Shot Settings","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461843","doi":"https://doi.org/10.1109/slt61566.2024.10832199"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092639643","display_name":"Yash Jogi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yash Jogi","raw_affiliation_strings":["Sprinklr,India"],"affiliations":[{"raw_affiliation_string":"Sprinklr,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859535","display_name":"Vaibhav Aggarwal","orcid":"https://orcid.org/0000-0002-7504-3297"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vaibhav Aggarwal","raw_affiliation_strings":["Sprinklr,India"],"affiliations":[{"raw_affiliation_string":"Sprinklr,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003878972","display_name":"Shabari S Nair","orcid":"https://orcid.org/0000-0001-9054-0147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shabari S Nair","raw_affiliation_strings":["Sprinklr,India"],"affiliations":[{"raw_affiliation_string":"Sprinklr,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102516412","display_name":"Yash Verma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yash Verma","raw_affiliation_strings":["Sprinklr,India"],"affiliations":[{"raw_affiliation_string":"Sprinklr,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061956581","display_name":"Aayush Kubba","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aayush Kubba","raw_affiliation_strings":["Sprinklr,India"],"affiliations":[{"raw_affiliation_string":"Sprinklr,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092639643"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7088615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9958000183105469,"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":0.9958000183105469,"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/T10028","display_name":"Topic Modeling","score":0.9919999837875366,"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":0.9911999702453613,"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":0.6640517711639404},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6586047410964966},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6187421679496765},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5609010457992554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4494738280773163},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41582149267196655},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41550135612487793},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17907920479774475},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1390281617641449},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.09867513179779053},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.05765002965927124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6640517711639404},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6586047410964966},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6187421679496765},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5609010457992554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4494738280773163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41582149267196655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41550135612487793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17907920479774475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1390281617641449},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09867513179779053},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.05765002965927124},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2799473636","https://openalex.org/W3016010032","https://openalex.org/W3020336359","https://openalex.org/W3036601975","https://openalex.org/W3095410713","https://openalex.org/W3097794466","https://openalex.org/W3100460087","https://openalex.org/W3101648800","https://openalex.org/W3119308075","https://openalex.org/W3198004110","https://openalex.org/W4224918838","https://openalex.org/W4226278401","https://openalex.org/W4311187265","https://openalex.org/W4319862261","https://openalex.org/W4319862635","https://openalex.org/W4365143687","https://openalex.org/W4385245566","https://openalex.org/W4385807453","https://openalex.org/W4385822890","https://openalex.org/W4385822953","https://openalex.org/W4389519450","https://openalex.org/W4391021545","https://openalex.org/W4392903078","https://openalex.org/W4392904451","https://openalex.org/W4402111365","https://openalex.org/W4402111737","https://openalex.org/W6771467084","https://openalex.org/W6778691839","https://openalex.org/W6780218876","https://openalex.org/W6791353385","https://openalex.org/W6810738896","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2296205523"],"abstract_inverted_index":{"Whisper,":[0],"despite":[1],"being":[2,24],"trained":[3],"on":[4],"680":[5],"K":[6],"hours":[7,57],"of":[8,58,80,88],"web-scaled":[9],"audio":[10],"data,":[11],"faces":[12],"difficulty":[13],"in":[14,34,78,86],"recognizing":[15],"rare":[16,81],"words":[17,82,89],"like":[18],"domain-specific":[19],"terms,":[20],"with":[21],"a":[22,39,75],"solution":[23],"contextual":[25,47,100],"biasing":[26,48,101],"through":[27],"prompting.":[28],"To":[29],"improve":[30],"upon":[31],"this":[32,35],"method,":[33],"paper,":[36],"we":[37],"propose":[38],"supervised":[40],"learning":[41],"strategy":[42],"to":[43,68,105],"fine-tune":[44],"Whisper":[45],"for":[46,63],"instruction.":[49],"We":[50],"demonstrate":[51],"that":[52],"by":[53],"using":[54],"only":[55],"670":[56],"Common":[59],"Voice":[60],"English":[61,72],"set":[62],"fine-tuning,":[64],"our":[65,98],"model":[66],"generalizes":[67,103],"11":[69],"diverse":[70],"opensource":[71],"datasets,":[73],"achieving":[74],"45.6%":[76],"improvement":[77,85],"recognition":[79,87],"and":[83],"60.8%":[84],"unseen":[90,107],"during":[91,108],"fine-tuning":[92],"over":[93],"the":[94],"baseline":[95],"method.":[96],"Surprisingly,":[97],"model\u2019s":[99],"ability":[102],"even":[104],"languages":[106],"fine-tuning.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}