{"id":"https://openalex.org/W7225732226","doi":"https://doi.org/10.31234/osf.io/kt58x","title":"Benchmarking an automated speech recognition pipeline for Spanish-English bilingual preschoolers: Quantifying language input and output in daylong recordings.","display_name":"Benchmarking an automated speech recognition pipeline for Spanish-English bilingual preschoolers: Quantifying language input and output in daylong recordings.","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225732226","doi":"https://doi.org/10.31234/osf.io/kt58x"},"language":"en","primary_location":{"id":"doi:10.31234/osf.io/kt58x","doi":"https://doi.org/10.31234/osf.io/kt58x","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/kt58x","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.31234/osf.io/kt58x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129549490","display_name":"Gaurab Subedi","orcid":"https://orcid.org/0009-0004-2967-0355","observed_orcids":["https://orcid.org/0009-0004-2967-0355"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaurab Subedi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0004-2967-0355","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057205161","display_name":"Marvin Lavechin","orcid":"https://orcid.org/0000-0002-6005-9368","observed_orcids":["https://orcid.org/0000-0002-6005-9368"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marvin Lavechin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056215625","display_name":"Jorge Ram\u00f3n Fonseca Cacho","orcid":"https://orcid.org/0000-0001-7917-5169","observed_orcids":["https://orcid.org/0000-0001-7917-5169"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jorge Fonseca","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7917-5169","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045730829","display_name":"Sarah Surrain","orcid":"https://orcid.org/0000-0002-6296-3182","observed_orcids":["https://orcid.org/0000-0002-6296-3182"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sarah Surrain","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6296-3182","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":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":0.9146000146865845,"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":0.9146000146865845,"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/T10730","display_name":"Language Development and Disorders","score":0.0674000009894371,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/T10403","display_name":"Phonetics and Phonology Research","score":0.006399999838322401,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796000003814697},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.59579998254776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5608999729156494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47360000014305115},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.3880000114440918},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31234/osf.io/kt58x","doi":"https://doi.org/10.31234/osf.io/kt58x","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/kt58x","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.31234/osf.io/kt58x","doi":"https://doi.org/10.31234/osf.io/kt58x","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/kt58x","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"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":[],"abstract_inverted_index":{"Measuring":[0],"how":[1,40],"much":[2],"of":[3,51,62,123,129,182,213],"each":[4,148],"language":[5,225],"bilingual":[6,65,214],"children":[7],"hear":[8],"and":[9,44,83,126,131,143,217,224],"use":[10],"in":[11,39,147,241],"their":[12],"daily":[13],"lives":[14],"requires":[15],"transcribing":[16],"long,":[17],"naturalistic":[18],"recordings,":[19],"which":[20],"is":[21,42],"too":[22],"costly":[23],"to":[24,46,75,100,139,167,171,178],"do":[25],"by":[26],"hand":[27],"at":[28,135,153],"scale.":[29],"We":[30],"benchmarked":[31],"four":[32],"WhisperX-based":[33],"automatic":[34],"speech":[35,41],"recognition":[36],"pipelines,":[37],"differing":[38],"located":[43],"attributed":[45,98],"speakers,":[47],"against":[48],"expert":[49,87],"transcripts":[50],"168":[52],"five-minute":[53],"clips":[54],"(14":[55],"hours)":[56],"drawn":[57],"from":[58,234],"daylong":[59],"home":[60],"recordings":[61],"14":[63],"Spanish--English":[64,236],"preschoolers.":[66],"Word":[67],"error":[68],"rates":[69],"across":[70],"pipelines":[71,208],"were":[72,169],"high":[73],"(69.5%":[74],"82.0%":[76],"overall),":[77],"compared":[78],"with":[79],"35.4%":[80],"(key":[81],"child)":[82],"53.9%":[84],"(adults)":[85],"between":[86],"coders.":[88],"Running":[89],"a":[90],"child-centered":[91],"voice":[92],"type":[93],"classifier":[94],"(VTC2)":[95],"before":[96,229],"transcription":[97],"words":[99,133,165,176],"speakers":[101,106],"far":[102],"better":[103],"than":[104,173],"labeling":[105],"afterwards;":[107],"we":[108],"retained":[109],"this":[110],"pipeline":[111],"(WER":[112],"=":[113,137],"71.4%).":[114],"Despite":[115],"word-level":[116],"errors,":[117],"it":[118],"preserved":[119],"the":[120,144,154],"rank":[121],"order":[122],"clips;":[124],"automated":[125],"manual":[127],"counts":[128,223],"total":[130,175],"distinct":[132,164],"correlated":[134],"r":[136],".83":[138],".93":[140],"for":[141,163,174],"adults":[142],"key":[145,190],"child":[146,218],"language.":[149],"Agreement":[150],"rose":[151],"further":[152],"recording":[155],"level.":[156],"Lexical":[157],"diversity":[158],"was":[159,184],"recovered":[160],"best:":[161],"slopes":[162],"(0.79":[166],"0.88)":[168],"closer":[170],"one":[172,235],"(0.53":[177],"0.77).":[179],"The":[180],"proportion":[181],"Spanish":[183],"underestimated":[185],"(adults:":[186],"77%":[187],"vs.":[188,193],"89%;":[189],"child:":[191],"70%":[192],"90%),":[194],"largely":[195],"because":[196],"WhisperX":[197],"output":[198],"short":[199],"English":[200],"phrases":[201],"on":[202],"brief,":[203],"unclear":[204],"audio.":[205],"Open,":[206],"inspectable":[207],"can":[209],"yield":[210],"language-specific":[211],"measures":[212],"adult":[215],"input":[216],"output,":[219],"but":[220],"precise":[221],"word":[222],"proportions":[226],"require":[227],"correction":[228],"direct":[230],"interpretation.":[231],"These":[232],"estimates,":[233],"community,":[237],"will":[238],"need":[239],"re-estimating":[240],"other":[242],"populations.":[243]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}