{"id":"https://openalex.org/W4415433777","doi":"https://doi.org/10.21437/interspeech.2025-342","title":"ASR-based segmentation for the analysis of larger child-speech datasets: Performance evaluation on vowels from Australian-English speaking children aged 4 to 11 years","display_name":"ASR-based segmentation for the analysis of larger child-speech datasets: Performance evaluation on vowels from Australian-English speaking children aged 4 to 11 years","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433777","doi":"https://doi.org/10.21437/interspeech.2025-342"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-342","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-342","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://handle.uba.uva.nl/personal/pure/en/publications/asrbased-segmentation-for-the-analysis-of-larger-childspeech-datasets(fdee9e7b-a4d4-465e-9ca7-da046666efc3).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069272117","display_name":"Rui Cai","orcid":"https://orcid.org/0000-0002-6499-2091"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057308995","display_name":"Titia Benders","orcid":"https://orcid.org/0000-0003-0143-2182"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Titia Benders","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15366066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4273","last_page":"4277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9929999709129333,"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":0.9929999709129333,"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":0.9797000288963318,"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":0.9488999843597412,"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/segmentation","display_name":"Segmentation","score":0.5164999961853027},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2743000090122223},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26820001006126404},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.25029999017715454}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41130000352859497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40790000557899475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35519999265670776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3050999939441681},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.275299996137619},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-342","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-342","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:dare.uva.nl:openaire_cris_publications/fdee9e7b-a4d4-465e-9ca7-da046666efc3","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/asrbased-segmentation-for-the-analysis-of-larger-childspeech-datasets(fdee9e7b-a4d4-465e-9ca7-da046666efc3).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cai, R & Benders, T 2025, 'ASR-based segmentation for the analysis of larger child-speech datasets : Performance evaluation on vowels from Australian-English speaking children aged 4 to 11 years', Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 26, pp. 4273-4277. https://doi.org/10.21437/Interspeech.2025-342","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:dare.uva.nl:openaire/fdee9e7b-a4d4-465e-9ca7-da046666efc3","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/fdee9e7b-a4d4-465e-9ca7-da046666efc3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"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":"Cai, R & Benders, T 2025, 'ASR-based segmentation for the analysis of larger child-speech datasets : Performance evaluation on vowels from Australian-English speaking children aged 4 to 11 years', Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 26, pp. 4273-4277. https://doi.org/10.21437/Interspeech.2025-342","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/fdee9e7b-a4d4-465e-9ca7-da046666efc3","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/asrbased-segmentation-for-the-analysis-of-larger-childspeech-datasets(fdee9e7b-a4d4-465e-9ca7-da046666efc3).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cai, R & Benders, T 2025, 'ASR-based segmentation for the analysis of larger child-speech datasets : Performance evaluation on vowels from Australian-English speaking children aged 4 to 11 years', Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 26, pp. 4273-4277. https://doi.org/10.21437/Interspeech.2025-342","raw_type":"info:eu-repo/semantics/article"},"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":{"Annotation":[0],"of":[1,43,50,89,136],"segment":[2,114],"boundaries":[3],"in":[4,62,77],"child":[5,34,137],"speech":[6],"presents":[7],"a":[8],"persistent":[9],"challenge,":[10],"particularly":[11],"with":[12],"large-scale":[13],"datasets.":[14],"While":[15],"auto-segmentation":[16],"methods":[17],"have":[18],"been":[19,27],"developed":[20],"for":[21,112],"adult":[22],"speech,":[23],"little":[24],"attention":[25],"has":[26],"paid":[28],"to":[29,41,79,122],"evaluating":[30],"their":[31],"performance":[32,42],"on":[33,120],"speech.":[35,138],"This":[36],"study":[37,58],"evaluates":[38],"factors":[39],"contributing":[40],"automatic":[44,125],"segmentation":[45,76],"by":[46],"analyzing":[47],"the":[48,71,85,90,103,107],"annotations":[49],"two":[51],"studies":[52],"into":[53,127],"Australian-English-speaking":[54],"children.":[55],"The":[56,66,81],"first":[57],"assesses":[59],"human-human":[60],"reliability":[61],"3-":[63],"and":[64,70,106],"12-year-olds.":[65],"second":[67],"compares":[68],"manual":[69],"Montreal":[72],"Forced":[73],"Aligner":[74],"(MFA)":[75],"4-":[78],"11-year-olds.":[80],"results":[82,117],"indicate":[83],"that":[84],"MFA":[86,108],"falls":[87],"short":[88],"human":[91,104],"annotator,":[92],"though":[93],"discrepancies":[94,101],"decrease":[95],"as":[96],"children":[97],"grow":[98],"older.":[99],"Systematic":[100],"between":[102],"annotator":[105],"suggest":[109],"different":[110],"criteria":[111],"placing":[113],"boundaries.":[115],"These":[116],"shed":[118],"light":[119],"how":[121],"incorporate":[123],"adult-based":[124],"aligners":[126],"semi-automatic":[128],"(and":[129],"thus:":[130],"still":[131],"partially":[132],"manual)":[133],"acoustic":[134],"analysis":[135]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-24T00:00:00"}