{"id":"https://openalex.org/W4401597889","doi":"https://doi.org/10.1109/icasspw62465.2024.10626001","title":"Leveraging Confidence Models for Identifying Challenging Data Subgroups in Speech Models","display_name":"Leveraging Confidence Models for Identifying Challenging Data Subgroups in Speech Models","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401597889","doi":"https://doi.org/10.1109/icasspw62465.2024.10626001"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626001","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083365850","display_name":"Alkis Koudounas","orcid":"https://orcid.org/0000-0003-4386-0409"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alkis Koudounas","raw_affiliation_strings":["Politecnico di Torino,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057352420","display_name":"Eliana Pastor","orcid":"https://orcid.org/0000-0002-3664-4137"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Eliana Pastor","raw_affiliation_strings":["Politecnico di Torino,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056273253","display_name":"Vittorio Mazzia","orcid":"https://orcid.org/0000-0002-7624-1850"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vittorio Mazzia","raw_affiliation_strings":["Amazon,Alexa AI,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI,Turin,Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087447838","display_name":"Manuel Giollo","orcid":"https://orcid.org/0000-0001-9434-2383"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Giollo","raw_affiliation_strings":["Amazon,Alexa AI,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI,Turin,Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038372751","display_name":"Thomas Gueudr\u00e9","orcid":"https://orcid.org/0000-0001-9462-3679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Gueudre","raw_affiliation_strings":["Amazon,Alexa AI,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI,Turin,Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093900662","display_name":"Elisa Reale","orcid":"https://orcid.org/0009-0005-1409-0136"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elisa Reale","raw_affiliation_strings":["Amazon,Alexa AI,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI,Turin,Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001986834","display_name":"Giuseppe Attanasio","orcid":"https://orcid.org/0000-0001-6945-3698"},"institutions":[{"id":"https://openalex.org/I71209653","display_name":"Bocconi University","ror":"https://ror.org/05crjpb27","country_code":"IT","type":"education","lineage":["https://openalex.org/I71209653"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Attanasio","raw_affiliation_strings":["Bocconi University,Milan,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bocconi University,Milan,Italy","institution_ids":["https://openalex.org/I71209653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001746215","display_name":"Luca Cagliero","orcid":"https://orcid.org/0000-0002-7185-5247"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Cagliero","raw_affiliation_strings":["Politecnico di Torino,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015516603","display_name":"Sandro Cumani","orcid":"https://orcid.org/0000-0001-6036-0065"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sandro Cumani","raw_affiliation_strings":["Politecnico di Torino,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050777140","display_name":"Luca de Alfaro","orcid":"https://orcid.org/0000-0003-3856-4576"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luca De Alfaro","raw_affiliation_strings":["University of California,Santa Cruz,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Santa Cruz,CA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001695309","display_name":"Elena Baralis","orcid":"https://orcid.org/0000-0001-9231-467X"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elena Baralis","raw_affiliation_strings":["Politecnico di Torino,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027227301","display_name":"Daniele Amberti","orcid":"https://orcid.org/0009-0009-8759-1424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniele Amberti","raw_affiliation_strings":["Amazon,Alexa AI,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI,Turin,Italy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"134","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8662999868392944,"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":0.8662999868392944,"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":0.7273725867271423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4524461627006531},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4423193633556366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4401395320892334},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4249369502067566},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.07024222612380981}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7273725867271423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4524461627006531},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4423193633556366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4401395320892334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4249369502067566},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.07024222612380981}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626001","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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":17,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1970329478","https://openalex.org/W2143693287","https://openalex.org/W2972584841","https://openalex.org/W2996275903","https://openalex.org/W3015634748","https://openalex.org/W3036601975","https://openalex.org/W3161324588","https://openalex.org/W3163169798","https://openalex.org/W3167533889","https://openalex.org/W3173173856","https://openalex.org/W3194438854","https://openalex.org/W3197580070","https://openalex.org/W3203388655","https://openalex.org/W4372270707","https://openalex.org/W4372346208","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"State-of-the-art":[0],"speech":[1,131,169],"models":[2,88,170],"may":[3],"exhibit":[4],"suboptimal":[5],"performance":[6],"in":[7,140,171],"specific":[8],"population":[9],"subgroups.":[10,84],"Detecting":[11],"these":[12,83],"challenging":[13,143],"cohorts":[14],"is":[15],"crucial":[16],"for":[17,25,120,162],"enhancing":[18],"model":[19,63],"robustness":[20,165],"and":[21,37,76,133,145,166],"fairness.":[22],"Traditional":[23],"methods":[24],"subgroup":[26,102,107,149],"identification":[27,103],"typically":[28],"rely":[29],"on":[30,100,129],"demographic":[31,111],"information":[32,92],"such":[33,41],"as":[34,158],"age,":[35],"gender,":[36],"origin.":[38],"However,":[39],"collecting":[40],"sensitive":[42,121],"data":[43,122],"at":[44,124],"deployment":[45,125],"time":[46],"can":[47],"be":[48],"impractical":[49],"or":[50],"unfeasible":[51],"due":[52],"to":[53,65,73,90],"privacy":[54],"concerns.This":[55],"paper":[56],"introduces":[57],"a":[58,159],"novel":[59],"Problematic":[60],"Subgroup":[61],"Identification":[62],"(PSI)":[64],"(i)":[66],"automatically":[67],"predict":[68],"if":[69],"an":[70,79,147],"utterance":[71],"belongs":[72],"problematic":[74,101],"subgroups":[75,144],"(ii)":[77],"provide":[78],"interpretable":[80,148],"representation":[81],"of":[82,95,156,168],"PSI":[85,109,157],"exploits":[86],"confidence":[87],"(CMs)":[89],"encode":[91],"about":[93],"sources":[94],"errors.":[96],"CM":[97],"fine-tuning":[98],"based":[99],"techniques":[104],"allows":[105],"accurate":[106],"identification.":[108],"leverages":[110],"features":[112],"only":[113],"during":[114],"its":[115],"training,":[116],"avoiding":[117],"the":[118,154,164],"need":[119],"collection":[123],"time.":[126],"Experimental":[127],"results":[128],"automatic":[130],"recognition":[132],"intent":[134],"classification":[135],"datasets":[136],"show":[137],"PSI\u2019s":[138],"effectiveness":[139],"both":[141],"identifying":[142],"providing":[146],"description.":[150],"These":[151],"findings":[152],"underscore":[153],"potential":[155],"valuable":[160],"tool":[161],"improving":[163],"fairness":[167],"real-world":[172],"applications.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}