{"id":"https://openalex.org/W4408354278","doi":"https://doi.org/10.1109/icassp49660.2025.10888254","title":"Adopting Whisper for Confidence Estimation","display_name":"Adopting Whisper for Confidence Estimation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354278","doi":"https://doi.org/10.1109/icassp49660.2025.10888254"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888254","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/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,Gurugram,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sprinklr,Gurugram,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shabari S Nair","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shabari S Nair","raw_affiliation_strings":["Sprinklr,Gurugram,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sprinklr,Gurugram,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040897977","display_name":"Yash Verma","orcid":"https://orcid.org/0000-0002-2670-380X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yash Verma","raw_affiliation_strings":["Sprinklr,Gurugram,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sprinklr,Gurugram,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092639643","display_name":"Yash Jogi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yash Jogi","raw_affiliation_strings":["Sprinklr,Gurugram,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sprinklr,Gurugram,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94735598,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.45010000467300415,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.45010000467300415,"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/T10734","display_name":"Information and Cyber Security","score":0.39329999685287476,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.585567831993103},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5676517486572266},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.48212146759033203},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28840312361717224},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13137760758399963},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07266896963119507},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.04299101233482361}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.585567831993103},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5676517486572266},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.48212146759033203},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28840312361717224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13137760758399963},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07266896963119507},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.04299101233482361}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888254","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/W34303869","https://openalex.org/W1494198834","https://openalex.org/W1966716734","https://openalex.org/W2034537249","https://openalex.org/W2095629250","https://openalex.org/W2127141656","https://openalex.org/W2189391786","https://openalex.org/W2950170869","https://openalex.org/W2962760690","https://openalex.org/W3011339933","https://openalex.org/W3015194534","https://openalex.org/W3020336359","https://openalex.org/W3095410713","https://openalex.org/W3119308075","https://openalex.org/W3161324588","https://openalex.org/W3163169798","https://openalex.org/W3197451691","https://openalex.org/W3203388655","https://openalex.org/W4234016251","https://openalex.org/W4319790622","https://openalex.org/W4319862635","https://openalex.org/W4385895497","https://openalex.org/W6728622933","https://openalex.org/W6739651123","https://openalex.org/W6739901393","https://openalex.org/W6771467084","https://openalex.org/W6773815586","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6810738896","https://openalex.org/W6839034341","https://openalex.org/W6847363464"],"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/W4396696052"],"abstract_inverted_index":{"Recent":[0],"research":[1],"on":[2,13,24,99,108],"word-level":[3,51],"confidence":[4,52,69],"estimation":[5],"for":[6],"speech":[7],"recognition":[8],"systems":[9],"has":[10],"primarily":[11],"focused":[12],"lightweight":[14],"models":[15],"known":[16],"as":[17],"Confidence":[18],"Estimation":[19],"Modules":[20],"(CEMs),":[21],"which":[22,60],"rely":[23],"hand-engineered":[25],"features":[26],"derived":[27],"from":[28],"Automatic":[29],"Speech":[30],"Recognition":[31],"(ASR)":[32],"outputs.":[33],"In":[34],"contrast,":[35],"we":[36,55],"propose":[37],"a":[38,57,92,123],"novel":[39],"end-to-end":[40],"approach":[41],"that":[42,83],"leverages":[43],"the":[44,61,84,100,105,113,119,128],"ASR":[45],"model":[46,63,116],"itself":[47],"(Whisper)":[48],"to":[49,66,91],"generate":[50],"scores.":[53],"Specifically,":[54],"introduce":[56],"method":[58],"in":[59,89],"Whisper":[62],"is":[64],"fine-tuned":[65,85,114],"produce":[67],"scalar":[68],"scores":[70],"given":[71],"an":[72],"audio":[73],"input":[74],"and":[75,103],"its":[76],"corresponding":[77],"hypothesis":[78],"transcript.":[79],"Our":[80],"experiments":[81],"demonstrate":[82],"Whisper-tiny":[86],"model,":[87],"comparable":[88],"size":[90],"strong":[93],"CEM":[94,106,120],"baseline,":[95],"achieves":[96],"similar":[97],"performance":[98],"in-domain":[101],"dataset":[102],"surpasses":[104],"baseline":[107,121],"eight":[109],"out-of-domain":[110],"datasets,":[111],"whereas":[112],"Whisper-large":[115],"consistently":[117],"outperforms":[118],"by":[122],"substantial":[124],"margin":[125],"across":[126],"all":[127],"datasets.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}