{"id":"https://openalex.org/W4415237717","doi":"https://doi.org/10.21437/interspeech.2025-1375","title":"Mispronunciation Detection Without L2 Pronunciation Dataset in Low-Resource Setting: A Case Study in Finland Swedish","display_name":"Mispronunciation Detection Without L2 Pronunciation Dataset in Low-Resource Setting: A Case Study in Finland Swedish","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415237717","doi":"https://doi.org/10.21437/interspeech.2025-1375"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1375","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.01156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068758223","display_name":"Nhan Phan","orcid":"https://orcid.org/0000-0003-2040-9834"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nhan Phan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070466290","display_name":"Mikko Kuronen","orcid":"https://orcid.org/0000-0001-5971-7063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikko Kuronen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057122832","display_name":"Maria Kautonen","orcid":"https://orcid.org/0000-0002-0688-7445"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Kautonen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054208696","display_name":"Riikka Ullakonoja","orcid":"https://orcid.org/0000-0002-9421-3706"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Riikka Ullakonoja","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016610998","display_name":"Anna von Zansen","orcid":"https://orcid.org/0000-0002-6444-7667"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anna von Zansen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082953089","display_name":"Yaroslav Getman","orcid":"https://orcid.org/0000-0003-4680-8294"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaroslav Getman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035401913","display_name":"Ekaterina Voskoboinik","orcid":"https://orcid.org/0009-0007-2691-5793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ekaterina Voskoboinik","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058277119","display_name":"Tam\u00e1s Gr\u00f3sz","orcid":"https://orcid.org/0000-0001-7918-9579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tam\u00e1s Gr\u00f3sz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5068758223"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15017345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2435","last_page":"2439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9958999752998352,"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":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6759999990463257},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5824999809265137},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.527999997138977},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.4875999987125397},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4489000141620636},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41339999437332153},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.39239999651908875},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.3434999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096999883651733},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6759999990463257},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5824999809265137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5813999772071838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5734999775886536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5436000227928162},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.527999997138977},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C2987567764","wikidata":"https://www.wikidata.org/wiki/Q125421","display_name":"Second language","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C2778883600","wikidata":"https://www.wikidata.org/wiki/Q2390977","display_name":"Language proficiency","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2502000033855438},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2025-1375","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.01156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.01156","pdf_url":"https://arxiv.org/pdf/2506.01156","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},{"id":"pmh:oai:jyx.jyu.fi:123456789/105027","is_oa":true,"landing_page_url":"http://urn.fi/URN:NBN:fi:jyu-202508276765","pdf_url":"https://jyx.jyu.fi/bitstreams/05ef291c-38cc-4d87-8299-2bad3e54f75a/download","source":{"id":"https://openalex.org/S4306400563","display_name":"Jyv\u00e4skyl\u00e4 University Digital Archive (University of Jyv\u00e4skyl\u00e4)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I94722563","host_organization_name":"University of Jyv\u00e4skyl\u00e4","host_organization_lineage":["https://openalex.org/I94722563"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"A4"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/138958","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/f002bfd9-9c74-4a3a-80ca-046b564c9995","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.01156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.01156","pdf_url":"https://arxiv.org/pdf/2506.01156","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7231237868","display_name":null,"funder_award_id":"103893","funder_id":"https://openalex.org/F4320322885","funder_display_name":"NordForsk"}],"funders":[{"id":"https://openalex.org/F4320322885","display_name":"NordForsk","ror":"https://ror.org/05bqzfg94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Mispronunciation":[0],"detection":[1],"(MD)":[2],"models":[3],"are":[4,15],"the":[5,84,132],"cornerstones":[6],"of":[7,49,61,95],"many":[8],"language":[9,25,51],"learning":[10],"applications.":[11],"Unfortunately,":[12],"most":[13],"systems":[14],"built":[16],"for":[17,43,90,114],"English":[18],"and":[19,56,80,127,137],"other":[20,115],"major":[21],"languages,":[22],"while":[23],"low-resourced":[24],"varieties,":[26],"such":[27,33],"as":[28],"Finland":[29],"Swedish":[30],"(FS),":[31],"lack":[32],"tools.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"introduce":[39],"our":[40,96],"MD":[41],"model":[42,72],"FS,":[44],"trained":[45,67],"on":[46,58],"89":[47],"hours":[48],"first":[50],"(L1)":[52],"speakers'":[53],"spontaneous":[54],"speech":[55],"tested":[57],"33":[59],"minutes":[60],"L2":[62,104],"transcribed":[63],"read-aloud":[64],"speech.":[65],"We":[66],"a":[68],"multilingual":[69],"wav2vec":[70],"2.0":[71],"with":[73,131],"entropy":[74],"regularization,":[75],"followed":[76],"by":[77],"temperature":[78],"scaling":[79],"top-k":[81],"normalization":[82],"after":[83],"inference":[85],"to":[86,123],"better":[87],"adapt":[88],"it":[89,112],"MD.":[91],"The":[92,106],"main":[93],"novelty":[94],"method":[97],"lies":[98],"in":[99],"its":[100],"simplicity,":[101],"requiring":[102],"minimal":[103],"data.":[105],"process":[107],"is":[108],"also":[109],"language-independent,":[110],"making":[111],"suitable":[113],"low-resource":[116],"languages.":[117],"Our":[118],"proposed":[119],"algorithm":[120],"allows":[121],"us":[122],"balance":[124],"Recall":[125,135],"(43.2%)":[126],"Precision":[128,138],"(29.8%),":[129],"compared":[130],"baseline":[133],"model's":[134],"(77.5%)":[136],"(17.6%).":[139]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-16T00:00:00"}