{"id":"https://openalex.org/W4408355855","doi":"https://doi.org/10.1109/icassp49660.2025.10890741","title":"Speech Few-Shot Learning for Language Learners\u2019 Speech Recognition","display_name":"Speech Few-Shot Learning for Language Learners\u2019 Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355855","doi":"https://doi.org/10.1109/icassp49660.2025.10890741"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101579966","display_name":"Jian Cheng","orcid":"https://orcid.org/0000-0002-3755-2517"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jian Cheng","raw_affiliation_strings":["Google LLC,Mountain View,USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,Mountain View,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075408736","display_name":"Sam Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Nguyen","raw_affiliation_strings":["Google LLC,Mountain View,USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,Mountain View,USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101579966"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02094509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8406000137329102,"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":0.8406000137329102,"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":0.8132961988449097},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6507302522659302},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4892265796661377},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4674950838088989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4224480986595154},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40125447511672974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132961988449097},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6507302522659302},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4892265796661377},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4674950838088989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4224480986595154},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40125447511672974}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1032614754","https://openalex.org/W2052086036","https://openalex.org/W3094704668","https://openalex.org/W3135339411","https://openalex.org/W3196589454","https://openalex.org/W3205665014","https://openalex.org/W4319163914","https://openalex.org/W4375869211","https://openalex.org/W4385822324","https://openalex.org/W4385987638","https://openalex.org/W4390041933","https://openalex.org/W4392679398","https://openalex.org/W4392909075","https://openalex.org/W4392931630","https://openalex.org/W4402111244","https://openalex.org/W4402111493","https://openalex.org/W4402112040","https://openalex.org/W4402112108","https://openalex.org/W4402112222","https://openalex.org/W4402115918","https://openalex.org/W4404782964","https://openalex.org/W6678106355","https://openalex.org/W6778883912","https://openalex.org/W6800751262","https://openalex.org/W6810334672","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6859925366","https://openalex.org/W6864255096","https://openalex.org/W6868703450","https://openalex.org/W6875352460","https://openalex.org/W6875676167"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"how":[3],"speech":[4,12,26,35,60,84,110,119,135],"recognition":[5],"accuracy":[6],"can":[7],"be":[8],"improved":[9,68],"using":[10],"the":[11,25,78,94,102],"few-shot":[13,36,85,120],"in-context":[14,115,121],"learning":[15,122],"capabilities":[16],"of":[17,27,104],"a":[18,62,88,124],"multimodal":[19],"foundation":[20],"model":[21],"when":[22],"applied":[23],"to":[24,74,77,127],"language":[28,45],"learners.":[29],"Our":[30],"proposed":[31],"method,":[32],"which":[33],"combines":[34],"with":[37,58],"context":[38,97],"prompting,":[39],"demonstrates":[40],"significant":[41],"improvements":[42],"in":[43,133],"recognizing":[44],"learners\u2019":[46],"accented":[47,59],"speech.":[48],"Evaluations":[49],"on":[50],"data":[51],"from":[52,72,96,108],"an":[53],"L2":[54],"English":[55],"test":[56],"set":[57],"produced":[61],"33.1%":[63],"relative":[64,90],"WER":[65,91],"reduction":[66,92],"and":[67,111],"target":[69],"word":[70],"recall":[71],"89%":[73],"97%":[75],"compared":[76],"Gemini":[79],"1.5":[80],"Pro":[81],"baseline.":[82],"Notably,":[83],"alone":[86],"contributes":[87],"9.8%":[89],"beyond":[93],"gains":[95],"prompting.":[98],"These":[99],"results":[100],"underscore":[101],"importance":[103],"incorporating":[105],"domain":[106],"knowledge":[107],"both":[109],"text":[112],"modalities":[113],"within":[114],"learning,":[116],"suggesting":[117],"that":[118],"offers":[123],"viable":[125],"alternative":[126],"resource-intensive":[128],"fine-tuning":[129],"for":[130],"addressing":[131],"challenges":[132],"atypical":[134],"recognition.":[136]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}