{"id":"https://openalex.org/W7223701034","doi":"https://doi.org/10.48550/arxiv.2610.32382","title":"Acoustic and Lexical Signals for Native Language Identification of Language Learners","display_name":"Acoustic and Lexical Signals for Native Language Identification of Language Learners","publication_year":2026,"publication_date":"2026-10-23","ids":{"openalex":"https://openalex.org/W7223701034","doi":"https://doi.org/10.48550/arxiv.2610.32382"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.32382","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.32382","pdf_url":"https://arxiv.org/pdf/2610.32382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.32382","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054143133","display_name":"Ahmet Yavuz Uluslu","orcid":"https://orcid.org/0009-0001-8117-8665","observed_orcids":["https://orcid.org/0009-0001-8117-8665"]},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["CH","GB"],"is_corresponding":false,"raw_author_name":"Uluslu, Ahmet Yavuz","raw_affiliation_strings":["ALTA Institute , Department of Engineering , University of Cambridge","Department of Computational Linguistics , University of Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALTA Institute , Department of Engineering , University of Cambridge","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Computational Linguistics , University of Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027476226","display_name":"Mengjie Qian","orcid":"https://orcid.org/0000-0003-2614-5411","observed_orcids":["https://orcid.org/0000-0003-2614-5411"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qian, Mengjie","raw_affiliation_strings":["ALTA Institute , Department of Engineering , University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALTA Institute , Department of Engineering , University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111076409","display_name":"Kate Knill","orcid":"https://orcid.org/0000-0003-1292-2769","observed_orcids":["https://orcid.org/0000-0003-1292-2769"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Knill, Kate","raw_affiliation_strings":["ALTA Institute , Department of Engineering , University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALTA Institute , Department of Engineering , University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219","observed_orcids":["https://orcid.org/0000-0002-5311-8219"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gales, Mark","raw_affiliation_strings":["ALTA Institute , Department of Engineering , University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALTA Institute , Department of Engineering , University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9609000086784363,"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":0.9609000086784363,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.020099999383091927,"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/T11309","display_name":"Music and Audio Processing","score":0.005900000222027302,"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/native-language-identification","display_name":"native language identification","score":0.9629999995231628},{"id":"https://openalex.org/keywords/second-language-learners","display_name":"second language learners","score":0.8930000066757202},{"id":"https://openalex.org/keywords/learner-english","display_name":"learner English","score":0.5569999814033508},{"id":"https://openalex.org/keywords/speech-transcripts","display_name":"speech transcripts","score":0.6299999952316284},{"id":"https://openalex.org/keywords/wavlm","display_name":"WavLM","score":0.7099999785423279},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.9800000190734863},{"id":"https://openalex.org/keywords/proficiency-level","display_name":"proficiency level","score":0.5419999957084656},{"id":"https://openalex.org/keywords/common-european-framework-of-reference-for-languages","display_name":"Common European Framework of Reference for Languages","score":0.8980000019073486},{"id":"https://openalex.org/keywords/acoustic-characteristics","display_name":"acoustic features","score":0.460999995470047},{"id":"https://openalex.org/keywords/lexical-features","display_name":"lexical features","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7396000027656555},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6190999746322632},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5831000208854675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.483599990606308},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46889999508857727},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.4133000075817108},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.33219999074935913},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.31929999589920044},{"id":"https://openalex.org/C2987567764","wikidata":"https://www.wikidata.org/wiki/Q125421","display_name":"Second language","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2778883600","wikidata":"https://www.wikidata.org/wiki/Q2390977","display_name":"Language proficiency","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.32382","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.32382","pdf_url":"https://arxiv.org/pdf/2610.32382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.32382","doi":"https://doi.org/10.48550/arxiv.2610.32382","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.32382","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.32382","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.32382","pdf_url":"https://arxiv.org/pdf/2610.32382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320273","display_name":"University of Cambridge","ror":"https://ror.org/013meh722"},{"id":"https://openalex.org/F4320327931","display_name":"Innosuisse - Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung","ror":"https://ror.org/05a2bhn71"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223701034.pdf","grobid_xml":"https://content.openalex.org/works/W7223701034.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W3197580070","https://openalex.org/W6891858958","https://openalex.org/W7160919852"],"related_works":["https://openalex.org/W4388854333","https://openalex.org/W3011206861","https://openalex.org/W4414861566","https://openalex.org/W2573460338","https://openalex.org/W115071186","https://openalex.org/W2787734627","https://openalex.org/W2789321368","https://openalex.org/W1548407218","https://openalex.org/W2914465356","https://openalex.org/W7017106468"],"abstract_inverted_index":{"Spoken":[0],"native":[1],"language":[2,7,180],"(L1)":[3],"identification":[4,39,160],"for":[5,27],"second":[6],"learners":[8],"has":[9,20],"traditionally":[10],"relied":[11],"on":[12,65],"acoustic":[13,127,162],"attributes":[14],"of":[15,37,166,178],"speech.":[16],"Comparatively":[17],"little":[18],"attention":[19],"been":[21],"paid":[22],"to":[23,115,144],"analysing":[24],"speech":[25,42,168],"transcripts":[26,45,66,93],"L1":[28,38,57,159],"traces.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"present":[34],"a":[35,47,54,60,75],"study":[36],"using":[40,74],"both":[41],"and":[43,67,147,163,169,175],"corresponding":[44],"from":[46,113,161],"spoken":[48],"learner":[49,102,167],"English":[50],"corpus.":[51],"We":[52],"compare":[53],"WavLM-based":[55],"audio":[56,84,140],"classifier":[58,63,85],"with":[59,101,117,124,151,173],"zero-shot":[61],"GPT-4o":[62],"operating":[64],"analyse":[68],"their":[69,97],"predictions":[70],"across":[71],"proficiency":[72,174],"levels":[73],"CEFR-balanced":[76],"evaluation":[77],"set.":[78],"Our":[79],"experiments":[80],"show":[81],"that":[82],"the":[83,87,176],"outperforms":[86],"transcript-based":[88],"approach":[89],"overall":[90],"when":[91],"full":[92,118],"are":[94],"available,":[95],"although":[96],"relative":[98],"strengths":[99],"vary":[100],"proficiency.":[103],"Audio":[104],"performs":[105,111,148],"better":[106,112],"at":[107],"A1,":[108],"whereas":[109,139],"text":[110],"A2":[114],"C1":[116],"transcripts.":[119],"Transcript-based":[120],"accuracy":[121],"generally":[122],"increases":[123],"proficiency,":[125],"while":[126],"performance":[128,171],"remains":[129],"comparatively":[130],"stable.":[131],"Restricting":[132],"transcript":[133],"length":[134,146],"substantially":[135],"reduces":[136],"text-based":[137],"accuracy,":[138],"is":[141],"less":[142],"sensitive":[143],"input":[145],"relatively":[149],"well":[150],"limited":[152],"input.":[153],"These":[154],"findings":[155],"provide":[156],"insights":[157],"into":[158],"textual":[164],"representations":[165],"how":[170],"varies":[172],"amount":[177],"available":[179],"material.":[181]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-10-27T00:00:00"}