{"id":"https://openalex.org/W4401117812","doi":"https://doi.org/10.1162/coli_a_00526","title":"Perception of Phonological Assimilation by Neural Speech Recognition Models","display_name":"Perception of Phonological Assimilation by Neural Speech Recognition Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401117812","doi":"https://doi.org/10.1162/coli_a_00526"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00526","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00526","pdf_url":null,"source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1162/coli_a_00526","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013578128","display_name":"Charlotte Pouw","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Charlotte Pouw","raw_affiliation_strings":["University of Amsterdam, Institute for Logic, Language and Computation. c.m.pouw@uva.nl"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Institute for Logic, Language and Computation. c.m.pouw@uva.nl","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016467685","display_name":"Marianne de Heer Kloots","orcid":"https://orcid.org/0000-0002-2640-6899"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marianne de Heer Kloots","raw_affiliation_strings":["University of Amsterdam, Institute for Logic, Language and Computation. m.l.s.deheerkloots@uva.nl"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Institute for Logic, Language and Computation. m.l.s.deheerkloots@uva.nl","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047382001","display_name":"Afra Alishahi","orcid":null},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Afra Alishahi","raw_affiliation_strings":["Tilburg University, Cognitive Science & Artificial Intelligence. a.alishahi@tilburguniversity.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tilburg University, Cognitive Science & Artificial Intelligence. a.alishahi@tilburguniversity.edu","institution_ids":["https://openalex.org/I193700539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007928903","display_name":"Willem Zuidema","orcid":"https://orcid.org/0000-0002-2362-5447"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Willem Zuidema","raw_affiliation_strings":["University of Amsterdam, Institute for Logic, Language and Computation. w.h.zuidema@uva.nl"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Institute for Logic, Language and Computation. w.h.zuidema@uva.nl","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7038,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84239281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"50","issue":"4","first_page":"1557","last_page":"1585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/utterance","display_name":"Utterance","score":0.6777860522270203},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6448794603347778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5610144734382629},{"id":"https://openalex.org/keywords/neurocomputational-speech-processing","display_name":"Neurocomputational speech processing","score":0.5556254982948303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5447347164154053},{"id":"https://openalex.org/keywords/assimilation","display_name":"Assimilation (phonology)","score":0.5307707190513611},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47850123047828674},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.4527093768119812},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4355957508087158},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.424045592546463},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3532721996307373},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.292726993560791}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6777860522270203},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6448794603347778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5610144734382629},{"id":"https://openalex.org/C202101335","wikidata":"https://www.wikidata.org/wiki/Q7002166","display_name":"Neurocomputational speech processing","level":4,"score":0.5556254982948303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5447347164154053},{"id":"https://openalex.org/C75649859","wikidata":"https://www.wikidata.org/wiki/Q148877","display_name":"Assimilation (phonology)","level":2,"score":0.5307707190513611},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47850123047828674},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.4527093768119812},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4355957508087158},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.424045592546463},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3532721996307373},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.292726993560791},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_a_00526","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00526","pdf_url":null,"source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:78ae59525abd45fb8f4477178b906fed","is_oa":false,"landing_page_url":"https://doaj.org/article/78ae59525abd45fb8f4477178b906fed","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00526","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00526","pdf_url":null,"source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G1650570625","display_name":"InDeep: Interpreting Deep Learning Models for Text and Sound","funder_award_id":"NWA.1292.19.399","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W9028451","https://openalex.org/W9762390","https://openalex.org/W1494198834","https://openalex.org/W1951934685","https://openalex.org/W1996079964","https://openalex.org/W2013543993","https://openalex.org/W2014652991","https://openalex.org/W2028630806","https://openalex.org/W2050866747","https://openalex.org/W2052156816","https://openalex.org/W2060689695","https://openalex.org/W2114393637","https://openalex.org/W2125199092","https://openalex.org/W2127141656","https://openalex.org/W2172066118","https://openalex.org/W2505429802","https://openalex.org/W2625455707","https://openalex.org/W2884225676","https://openalex.org/W2964222268","https://openalex.org/W2979826702","https://openalex.org/W2990597852","https://openalex.org/W3036601975","https://openalex.org/W3105148948","https://openalex.org/W3115586233","https://openalex.org/W3127686677","https://openalex.org/W3211278025","https://openalex.org/W3216401400","https://openalex.org/W4226380987","https://openalex.org/W4231003508","https://openalex.org/W4246991306","https://openalex.org/W4248968314","https://openalex.org/W4253213911","https://openalex.org/W4256717825","https://openalex.org/W4288072840","https://openalex.org/W4367694478","https://openalex.org/W4385571392","https://openalex.org/W4385823328","https://openalex.org/W4389518242","https://openalex.org/W4391099575","https://openalex.org/W4394773771","https://openalex.org/W6780218876","https://openalex.org/W6785887628","https://openalex.org/W6789826613","https://openalex.org/W6846261036","https://openalex.org/W6847363464","https://openalex.org/W6851934580"],"related_works":["https://openalex.org/W2085161773","https://openalex.org/W2138468535","https://openalex.org/W2119928982","https://openalex.org/W2092804354","https://openalex.org/W577099509","https://openalex.org/W2556765287","https://openalex.org/W4248307672","https://openalex.org/W3202371450","https://openalex.org/W1988234613","https://openalex.org/W2593662288"],"abstract_inverted_index":{"Abstract":[0],"Human":[1],"listeners":[2,19],"effortlessly":[3],"compensate":[4,68],"for":[5,69],"phonological":[6,135,155],"changes":[7],"during":[8,71],"speech":[9,49],"perception,":[10],"often":[11],"unconsciously":[12],"inferring":[13],"the":[14,21,39,47,58,65,91,103,130,150],"intended":[15],"sounds.":[16],"For":[17],"example,":[18],"infer":[20],"underlying":[22,117],"/n/":[23],"when":[24],"hearing":[25],"an":[26],"utterance":[27],"such":[28],"as":[29],"\u201cclea[m]":[30],"pan\u201d,":[31],"where":[32],"[m]":[33],"arises":[34],"from":[35,111],"place":[36],"assimilation":[37,70],"to":[38,67,115,138],"following":[40],"labial":[41],"[p].":[42],"This":[43],"article":[44],"explores":[45],"how":[46,82],"neural":[48,158],"recognition":[50],"model":[51,66,104,131],"Wav2Vec2":[52],"perceives":[53],"assimilated":[54,109],"sounds,":[55],"and":[56,152,161],"identifies":[57],"linguistic":[59,84],"knowledge":[60],"that":[61,102,129],"is":[62],"implemented":[63],"by":[64],"Automatic":[72],"Speech":[73],"Recognition":[74],"(ASR).":[75],"Using":[76],"psycholinguistic":[77],"stimuli,":[78],"we":[79],"systematically":[80],"analyze":[81],"various":[83],"context":[85,136],"cues":[86,137],"influence":[87],"compensation":[88],"patterns":[89],"in":[90,119,154],"model\u2019s":[92],"output.":[93],"Complementing":[94],"these":[95],"behavioral":[96],"experiments,":[97],"our":[98,124],"probing":[99],"experiments":[100,127],"indicate":[101],"shifts":[105],"its":[106,120],"interpretation":[107],"of":[108],"sounds":[110],"their":[112,116],"acoustic":[113],"form":[114,118],"final":[121],"layers.":[122],"Finally,":[123],"causal":[125],"intervention":[126],"suggest":[128],"relies":[132],"on":[133],"minimal":[134],"accomplish":[139],"this":[140],"shift.":[141],"These":[142],"findings":[143],"represent":[144],"a":[145],"step":[146],"towards":[147],"better":[148],"understanding":[149],"similarities":[151],"differences":[153],"processing":[156],"between":[157],"ASR":[159],"models":[160],"humans.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}
