{"id":"https://openalex.org/W4391697095","doi":"https://doi.org/10.1109/taslp.2024.3363447","title":"Towards Comprehensive Subgroup Performance Analysis in Speech Models","display_name":"Towards Comprehensive Subgroup Performance Analysis in Speech Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391697095","doi":"https://doi.org/10.1109/taslp.2024.3363447"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3363447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3363447","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":"https://orcid.org/0000-0003-4386-0409","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":"https://orcid.org/0000-0002-3664-4137","affiliations":[{"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":["MilaNLP Group and the Data and Marketing Insights Unit, Bocconi Institute for Data Science and Analysis, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6945-3698","affiliations":[{"raw_affiliation_string":"MilaNLP Group and the Data and Marketing Insights Unit, Bocconi Institute for Data Science and Analysis, 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":["AGI, Amazon, Turin, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7624-1850","affiliations":[{"raw_affiliation_string":"AGI, 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":["AGI, Amazon, Turin, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9434-2383","affiliations":[{"raw_affiliation_string":"AGI, 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":["AGI, Amazon, Turin, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9462-3679","affiliations":[{"raw_affiliation_string":"AGI, Amazon, 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":["AGI, Amazon, Turin, Italy"],"raw_orcid":"https://orcid.org/0009-0005-1409-0136","affiliations":[{"raw_affiliation_string":"AGI, 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"],"raw_orcid":"https://orcid.org/0000-0002-7185-5247","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":"https://orcid.org/0000-0001-6036-0065","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, USA"],"raw_orcid":"https://orcid.org/0000-0003-3856-4576","affiliations":[{"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"],"raw_orcid":"https://orcid.org/0000-0001-9231-467X","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":["AGI, Amazon, Turin, Italy"],"raw_orcid":"https://orcid.org/0009-0009-8759-1424","affiliations":[{"raw_affiliation_string":"AGI, 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":1.9449,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87156571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"1468","last_page":"1480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.7685815691947937},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6709136962890625},{"id":"https://openalex.org/keywords/demographics","display_name":"Demographics","score":0.6274064779281616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.570095956325531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48796266317367554},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.47435057163238525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4225088357925415},{"id":"https://openalex.org/keywords/subgroup-analysis","display_name":"Subgroup analysis","score":0.4147719740867615},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3683606684207916},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13297873735427856},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10032445192337036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7685815691947937},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6709136962890625},{"id":"https://openalex.org/C2780084366","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demographics","level":2,"score":0.6274064779281616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.570095956325531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48796266317367554},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.47435057163238525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4225088357925415},{"id":"https://openalex.org/C187960798","wikidata":"https://www.wikidata.org/wiki/Q7631152","display_name":"Subgroup analysis","level":3,"score":0.4147719740867615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3683606684207916},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13297873735427856},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10032445192337036},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3363447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3363447","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W121174314","https://openalex.org/W1494198834","https://openalex.org/W1990942610","https://openalex.org/W1996512145","https://openalex.org/W2106491399","https://openalex.org/W2146334809","https://openalex.org/W2163089518","https://openalex.org/W2397474108","https://openalex.org/W2562335618","https://openalex.org/W2908285010","https://openalex.org/W2941689885","https://openalex.org/W2964959870","https://openalex.org/W2972584841","https://openalex.org/W3035503910","https://openalex.org/W3038342317","https://openalex.org/W3100460087","https://openalex.org/W3167533889","https://openalex.org/W3173173856","https://openalex.org/W3197580070","https://openalex.org/W3197613133","https://openalex.org/W3198429080","https://openalex.org/W3199192485","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W3215236363","https://openalex.org/W3217246256","https://openalex.org/W4252403066","https://openalex.org/W4281762205","https://openalex.org/W4293023585","https://openalex.org/W4372346208","https://openalex.org/W4385822487","https://openalex.org/W4385823176","https://openalex.org/W4385823265","https://openalex.org/W4386898608","https://openalex.org/W6628750762","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W3121380072","https://openalex.org/W2058403539","https://openalex.org/W2333615638","https://openalex.org/W2602311653","https://openalex.org/W2964230772","https://openalex.org/W2768231286","https://openalex.org/W2973958681","https://openalex.org/W2942793592","https://openalex.org/W2409976527","https://openalex.org/W626576356"],"abstract_inverted_index":{"The":[0,149],"evaluation":[1],"of":[2,20,61,98,106,171],"spoken":[3],"language":[4],"understanding":[5],"(SLU)":[6],"systems":[7],"is":[8],"often":[9],"restricted":[10],"to":[11,34,78,143],"assessing":[12],"their":[13],"global":[14],"performance":[15,42,84,126],"or":[16,133],"examining":[17],"predefined":[18],"subgroups":[19,54,90],"interest.":[21],"However,":[22],"a":[23,71,177],"more":[24],"detailed":[25],"analysis":[26],"at":[27,58,116],"the":[28,32,59,96,104,111,117,169,172],"subgroup":[29,99,118,125],"level":[30,60],"has":[31],"potential":[33],"uncover":[35],"valuable":[36],"insights":[37],"into":[38],"how":[39],"speech":[40,67,164],"system":[41],"differs":[43],"across":[44],"various":[45],"subgroups.":[46],"In":[47],"this":[48],"work,":[49],"we":[50],"identify":[51,121],"biased":[52],"data":[53,89],"and":[55,66,75,82,114,138,158,166],"describe":[56],"them":[57],"user":[62],"demographics,":[63],"recording":[64],"conditions,":[65],"targets.":[68],"We":[69,86,101,120],"propose":[70],"new":[72],"task-,":[73],"model-":[74],"dataset-agnostic":[76],"approach":[77,174],"detect":[79,87],"significant":[80,122],"intra-":[81],"cross-model":[83],"gaps.":[85],"problematic":[88],"in":[91,124,130,146,175],"SLU":[92,108,154,179],"models":[93,109,128],"by":[94],"leveraging":[95],"notion":[97],"divergence.":[100],"also":[102],"compare":[103],"outcome":[105],"different":[107,129,160],"on":[110,152],"same":[112],"dataset":[113],"task":[115],"level.":[119],"gaps":[123],"between":[127],"size,":[131],"architecture,":[132],"pre-training":[134],"objectives,":[135],"including":[136],"multi-lingual":[137],"mono-lingual":[139],"models,":[140,155],"yet":[141],"comparable":[142],"each":[144],"other":[145],"overall":[147],"performance.":[148],"results,":[150],"obtained":[151],"two":[153],"four":[156],"datasets,":[157],"three":[159],"tasks\u2013intent":[161],"classification,":[162],"automatic":[163],"recognition,":[165],"emotion":[167],"recognition\u2013confirm":[168],"effectiveness":[170],"proposed":[173],"providing":[176],"nuanced":[178],"model":[180],"assessment.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
