{"id":"https://openalex.org/W4415433452","doi":"https://doi.org/10.21437/interspeech.2025-1030","title":"A semi-automatic pipeline for transcribing and segmenting child speech","display_name":"A semi-automatic pipeline for transcribing and segmenting child speech","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433452","doi":"https://doi.org/10.21437/interspeech.2025-1030"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1030","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1030","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/53360.html>","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092639616","display_name":"Polychronia Christodoulidou","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Polychronia Christodoulidou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005884792","display_name":"James T. Tanner","orcid":"https://orcid.org/0000-0001-8143-2099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Tanner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006724741","display_name":"Jane Stuart\u2010Smith","orcid":"https://orcid.org/0000-0001-7400-9436"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jane Stuart-Smith","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109548899","display_name":"Michael McAuliffe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael McAuliffe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021831371","display_name":"Mridhula Murali","orcid":"https://orcid.org/0000-0001-5450-6419"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mridhula Murali","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057379107","display_name":"Amy Smith","orcid":"https://orcid.org/0009-0009-3999-2354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amy Smith","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068373762","display_name":"Lauren Taylor","orcid":"https://orcid.org/0000-0002-9985-9768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lauren Taylor","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075948249","display_name":"Joanne Cleland","orcid":"https://orcid.org/0000-0002-0660-1646"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joanne Cleland","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017755737","display_name":"Anja Kuschmann","orcid":"https://orcid.org/0000-0001-5396-9008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anja Kuschmann","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5092639616"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16695067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4278","last_page":"4282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9228000044822693,"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/T12031","display_name":"Speech and dialogue systems","score":0.9228000044822693,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9053999781608582,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7139999866485596},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.6818000078201294},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4659999907016754},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4544000029563904},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.42320001125335693},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4140999913215637},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39500001072883606},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.34310001134872437}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7139999866485596},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6818000078201294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6811000108718872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6040999889373779},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30570000410079956},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1030","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1030","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:eprints.gla.ac.uk:356888","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/53360.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:356888","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/53360.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"evaluates":[2],"both":[3,66],"automated":[4],"transcription":[5],"(WhisperX)":[6],"and":[7,59],"forced":[8,42],"alignment":[9,43],"(MFA)":[10],"in":[11],"developing":[12],"a":[13,28],"semi-automated":[14],"pipeline":[15],"for":[16,65],"obtaining":[17],"acoustic":[18,48,74,85],"vowel":[19,49],"measures":[20,50],"from":[21,24],"field":[22],"recordings":[23],"275":[25],"children":[26],"speaking":[27],"non-standard,":[29],"English":[30],"dialect,":[31],"Scottish":[32],"English.":[33],"As":[34],"expected,":[35],"manual":[36],"correction":[37],"of":[38,47,69,84],"speech":[39,57,79],"transcriptions":[40],"before":[41],"improves":[44,81],"the":[45,70,77,82],"quality":[46,83],"with":[51],"respect":[52],"to":[53],"manually-annotated":[54],"data,":[55],"though":[56,87],"style":[58],"recording":[60],"environment":[61],"present":[62],"some":[63],"challenges":[64],"tools.":[67],"Adaptation":[68],"MFA":[71],"pre-trained":[72],"english_us_arpa":[73],"model":[75],"towards":[76],"children's":[78],"also":[80],"measures,":[86],"greater":[88],"improvement":[89],"was":[90],"not":[91],"found":[92],"by":[93],"increasing":[94],"training":[95],"sample":[96],"size.":[97]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}
