{"id":"https://openalex.org/W4372346208","doi":"https://doi.org/10.1109/icassp49357.2023.10095284","title":"Exploring Subgroup Performance in End-to-End Speech Models","display_name":"Exploring Subgroup Performance in End-to-End Speech Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346208","doi":"https://doi.org/10.1109/icassp49357.2023.10095284"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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","Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]},{"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","Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]},{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"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","Bocconi University, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bocconi University,Milan,Italy","institution_ids":["https://openalex.org/I71209653"]},{"raw_affiliation_string":"Bocconi University, Milan, Italy","institution_ids":["https://openalex.org/I71209653"]}]},{"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":["Alexa AI, Amazon,Turin,Italy","Alexa AI, Amazon, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Turin,Italy","institution_ids":[]},{"raw_affiliation_string":"Alexa AI, Amazon, 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":["Alexa AI, Amazon,Turin,Italy","Alexa AI, Amazon, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Turin,Italy","institution_ids":[]},{"raw_affiliation_string":"Alexa AI, Amazon, 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":["Alexa AI, Amazon,Turin,Italy","Alexa AI, Amazon, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Turin,Italy","institution_ids":[]},{"raw_affiliation_string":"Alexa AI, Amazon, Turin, Italy","institution_ids":[]}]},{"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","Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]},{"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,USA","University of California, Santa Cruz, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Santa Cruz,CA,USA","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"University of California, Santa Cruz, CA, USA","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","Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]},{"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":["Alexa AI, Amazon,Turin,Italy","Alexa AI, Amazon, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon,Turin,Italy","institution_ids":[]},{"raw_affiliation_string":"Alexa AI, Amazon, 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":11,"citation_normalized_percentile":null,"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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/T12031","display_name":"Speech and dialogue systems","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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8005470633506775},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7768014073371887},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6475407481193542},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5941944122314453},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5236361026763916},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4932946562767029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4334877133369446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33603864908218384},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33496686816215515},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10677820444107056},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09881481528282166}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8005470633506775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7768014073371887},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6475407481193542},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5941944122314453},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5236361026763916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4932946562767029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4334877133369446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33603864908218384},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33496686816215515},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10677820444107056},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09881481528282166},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321499","display_name":"Fondazione Cariplo","ror":"https://ror.org/01gb56c55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2963198001","https://openalex.org/W2972584841","https://openalex.org/W3012624518","https://openalex.org/W3036601975","https://openalex.org/W3147107444","https://openalex.org/W3173173856","https://openalex.org/W3173326111","https://openalex.org/W3197580070","https://openalex.org/W3197613133","https://openalex.org/W3199192485","https://openalex.org/W3209059054","https://openalex.org/W3215236363","https://openalex.org/W3217246256","https://openalex.org/W4296069263","https://openalex.org/W6775697032","https://openalex.org/W6780218876","https://openalex.org/W6793191273","https://openalex.org/W6840924084"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248","https://openalex.org/W2768810474"],"abstract_inverted_index":{"End-to-End":[0],"Spoken":[1],"Language":[2],"Understanding":[3],"models":[4,106,137],"are":[5,50,138],"generally":[6],"evaluated":[7],"according":[8],"to":[9,149],"their":[10],"overall":[11],"accuracy,":[12],"or":[13,96,147],"separately":[14],"on":[15,71,108,113],"(a":[16],"priori":[17],"defined)":[18],"data":[19],"subgroups":[20,38,143],"of":[21,47,80,105,133],"interest.":[22],"We":[23],"propose":[24],"a":[25,44,52,127],"technique":[26,68],"for":[27],"analyzing":[28],"model":[29,74,88],"performance":[30,89,104,134],"at":[31],"the":[32,102,114,142,152],"subgroup":[33],"level,":[34],"which":[35],"considers":[36],"all":[37],"that":[39,144],"can":[40,58],"be":[41],"defined":[42],"via":[43],"given":[45],"set":[46],"metadata":[48,57],"and":[49,64,111,129],"above":[51],"specified":[53],"minimum":[54],"size.":[55],"The":[56,119],"represent":[59],"user":[60],"characteristics,":[61],"recording":[62],"conditions,":[63],"speech":[65],"targets.":[66],"Our":[67],"is":[69],"based":[70,107],"advances":[72],"in":[73],"bias":[75,97],"analysis,":[76],"enabling":[77],"efficient":[78],"exploration":[79],"resulting":[81],"subgroups.":[82],"A":[83],"fine-grained":[84],"analysis":[85,125],"reveals":[86,126],"how":[87,123],"varies":[90],"across":[91],"sub-groups,":[92],"identifying":[93,141],"modeling":[94],"issues":[95],"towards":[98],"specific":[99],"subgroups.We":[100],"compare":[101],"subgroup-level":[103,124],"wav2vec":[109],"2.0":[110],"HuBERT":[112],"Fluent":[115],"Speech":[116],"Commands":[117],"dataset.":[118],"experimental":[120],"results":[121],"illustrate":[122],"finer":[128],"more":[130],"complete":[131],"picture":[132],"changes":[135],"when":[136],"replaced,":[139],"automatically":[140],"most":[145],"benefit":[146,150],"fail":[148],"from":[151],"change.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}