{"id":"https://openalex.org/W7204178692","doi":"https://doi.org/10.1121/10.0045413","title":"Forced alignment of Istro-Venetian speech via neural versus non-neural models","display_name":"Forced alignment of Istro-Venetian speech via neural versus non-neural models","publication_year":2026,"publication_date":"2026-08-01","ids":{"openalex":"https://openalex.org/W7204178692","doi":"https://doi.org/10.1121/10.0045413"},"language":"en","primary_location":{"id":"doi:10.1121/10.0045413","doi":"https://doi.org/10.1121/10.0045413","is_oa":false,"landing_page_url":"https://doi.org/10.1121/10.0045413","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},"volume":null,"type":"conference-abstract","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/A5068148505","display_name":"Austin Brailey-Jones","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Jones","raw_affiliation_strings":["Dept. of Linguist, Univ. of Georgia, Athens, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Linguist, Univ. of Georgia, Athens, GA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129155735","display_name":"Massimo Daul","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Massimo Daul","raw_affiliation_strings":["New York Univ., New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York Univ., New York, NY","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029560404","display_name":"Margaret E. L. Renwick","orcid":"https://orcid.org/0000-0002-8759-1717","observed_orcids":["https://orcid.org/0000-0002-8759-1717"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Margaret E. Renwick","raw_affiliation_strings":["Dept. of Cognit. Sci., Johns Hopkins Univ., 3400 N. Charles St., Baltimore, MD 21218, mrenwick@jhu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Cognit. Sci., Johns Hopkins Univ., 3400 N. Charles St., Baltimore, MD 21218, mrenwick@jhu.edu","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000500620","display_name":"Zvjezdana Vrzi\u0107","orcid":"https://orcid.org/0000-0002-4028-8788","observed_orcids":["https://orcid.org/0000-0002-4028-8788"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zvjezdana Vrzic","raw_affiliation_strings":["Linguist Dept., New York Univ., New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguist Dept., New York Univ., New York, NY","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"John Hale","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Hale","raw_affiliation_strings":["Dept. of Cognit. Sci., Johns Hopkins Univ., Baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Cognit. Sci., Johns Hopkins Univ., Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107377564","display_name":"Keith Langston","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keith Langston","raw_affiliation_strings":["Dept. of Linguist, Univ. of Georgia, Athens, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Linguist, Univ. of Georgia, Athens, GA","institution_ids":["https://openalex.org/I165733156"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"159","issue":"4_Supplement","first_page":"A161","last_page":"A161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00039999998989515007,"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/T10860","display_name":"Speech and Audio Processing","score":0.0003000000142492354,"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/forced-alignment","display_name":"forced alignment","score":0.9940000176429749},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9490000009536743},{"id":"https://openalex.org/keywords/montreal-forced-aligner","display_name":"Montreal Forced Aligner","score":0.906000018119812},{"id":"https://openalex.org/keywords/word-alignment","display_name":"word alignment","score":0.7360000014305115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7179999947547913},{"id":"https://openalex.org/keywords/speech-transcription","display_name":"speech transcription","score":0.5569999814033508},{"id":"https://openalex.org/keywords/gaussian-mixture-hidden-markov-model","display_name":"Gaussian mixture hidden Markov model","score":0.8109999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7662000060081482},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7390000224113464},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6498000025749207},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5774999856948853},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44269999861717224},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4172999858856201},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C102830678","wikidata":"https://www.wikidata.org/wiki/Q7858684","display_name":"Two-alternative forced choice","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1121/10.0045413","doi":"https://doi.org/10.1121/10.0045413","is_oa":false,"landing_page_url":"https://doi.org/10.1121/10.0045413","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3217686684","https://openalex.org/W7110691195","https://openalex.org/W4321276228","https://openalex.org/W7135769468","https://openalex.org/W2921849847","https://openalex.org/W7221783883","https://openalex.org/W4416874080","https://openalex.org/W2964102148","https://openalex.org/W2965698119","https://openalex.org/W7064339829"],"abstract_inverted_index":{"Forced":[0,72],"aligners":[1],"are":[2],"an":[3],"essential":[4],"tool":[5],"to":[6,9,57,78,145],"facilitate":[7],"access":[8],"the":[10,55,67,70,83],"word":[11,121],"and":[12,26,62,75,148],"phone":[13],"level":[14],"of":[15,69,124],"speech":[16,49],"data,":[17],"but":[18],"they":[19,152],"rely":[20],"on":[21,107,133,157],"acoustic":[22,60],"models,":[23,102],"pronunciation":[24],"dictionaries,":[25],"complete":[27],"word-level":[28,38,80],"transcriptions":[29,118,138],"that":[30,92,113,139],"may":[31,153],"not":[32],"exist":[33],"for":[34,47,82],"low-resource":[35,84,134],"languages.":[36],"Alternatively,":[37],"alignments":[39,81],"can":[40,116,129,140],"be":[41,141],"extracted":[42],"from":[43],"neural":[44],"network-based":[45],"tools":[46],"automatic":[48],"recognition":[50],"like":[51],"Wav2Vec-BERT":[52,76,105,114],"2.0,":[53],"avoiding":[54],"need":[56],"create":[58],"bespoke":[59],"models":[61,98,128],"dictionaries.":[63],"This":[64],"paper":[65],"compares":[66],"ability":[68],"Montreal":[71],"Aligner":[73],"(MFA)":[74],"2.0":[77,106,115],"produce":[79,117],"variety":[85],"Istro-Venetian,":[86],"spoken":[87],"in":[88],"Croatia.":[89],"Results":[90],"indicate":[91],"MFA,":[93],"which":[94],"uses":[95],"Gaussian":[96],"mixture":[97],"with":[99,119,149],"hidden":[100],"Markov":[101],"significantly":[103],"outperforms":[104],"forced":[108,146,158],"alignment.":[109,159],"However,":[110],"we":[111],"show":[112],"a":[120],"error":[122],"rate":[123],"only":[125],"14.4%.":[126],"Neural":[127],"thus":[130],"aid":[131],"research":[132],"languages":[135],"by":[136],"creating":[137],"used":[142],"as":[143],"input":[144],"aligners,":[147],"sufficient":[150],"data":[151],"also":[154],"perform":[155],"acceptably":[156]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-08-26T00:00:00"}