{"id":"https://openalex.org/W4415433961","doi":"https://doi.org/10.21437/interspeech.2025-491","title":"Automatic classification of stop realisation with wav2vec2.0","display_name":"Automatic classification of stop realisation with wav2vec2.0","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433961","doi":"https://doi.org/10.21437/interspeech.2025-491"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-491","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-491","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/A5113607922","display_name":"James Tanner","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"James Tanner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050873228","display_name":"Morgan Sonderegger","orcid":"https://orcid.org/0000-0001-7675-2370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morgan Sonderegger","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/A5049111965","display_name":"Jeff Mielke","orcid":"https://orcid.org/0009-0002-9882-8254"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeff Mielke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086480059","display_name":"Tyler Kendall","orcid":"https://orcid.org/0000-0002-0989-1765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tyler Kendall","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113607922"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29678013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2270","last_page":"2274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14276","display_name":"Power Systems and Technologies","score":0.1386999934911728,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14276","display_name":"Power Systems and Technologies","score":0.1386999934911728,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7890999913215637},{"id":"https://openalex.org/keywords/realisation","display_name":"Realisation","score":0.7383000254631042},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5960999727249146},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4156999886035919},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.39010000228881836},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.3874000012874603},{"id":"https://openalex.org/keywords/phonetics","display_name":"Phonetics","score":0.3495999872684479}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7890999913215637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7594000101089478},{"id":"https://openalex.org/C2779462738","wikidata":"https://www.wikidata.org/wiki/Q17146409","display_name":"Realisation","level":2,"score":0.7383000254631042},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5960999727249146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5738000273704529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5601999759674072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5526999831199646},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3874000012874603},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3481999933719635},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.32280001044273376},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.2651999890804291},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C3019831412","wikidata":"https://www.wikidata.org/wiki/Q5778278","display_name":"Fully automatic","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-491","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-491","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:356969","is_oa":false,"landing_page_url":"http://eprints.gla.ac.uk/view/author/53360.html>","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:eprints.gla.ac.uk:356969","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:356969","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"phonetic":[1,25,51,130],"research":[2,131],"regularly":[3],"makes":[4],"use":[5],"of":[6,12,22,84,99,107,119,129],"automatic":[7,93,115],"tools":[8,17,112],"for":[9,19,113],"the":[10,20,28,92,105,114,127],"annotation":[11,21,116],"speech":[13,44,81,109,120],"data,":[14,122],"however":[15],"few":[16],"exist":[18],"many":[23],"variable":[24],"phenomena.":[26],"At":[27],"same":[29],"time,":[30],"pre-trained":[31,108],"self-supervised":[32],"models,":[33],"such":[34],"as":[35,111],"wav2vec2.0,":[36],"have":[37],"been":[38],"shown":[39],"to":[40,61,125],"perform":[41],"well":[42],"at":[43],"classification":[45],"tasks":[46],"and":[47,73,79,95,117],"latently":[48],"encode":[49],"fine-grained":[50],"information.":[52],"We":[53],"demonstrate":[54,104],"that":[55],"wav2vec2.0":[56],"models":[57,110],"can":[58],"be":[59],"trained":[60],"automatically":[62],"classify":[63],"stop":[64,87],"burst":[65],"presence":[66],"with":[67,91,132],"high":[68],"accuracy":[69],"in":[70,86],"both":[71,77],"English":[72],"Japanese,":[74],"robust":[75],"across":[76],"finely-curated":[78],"unprepared":[80],"corpora.":[82],"Patterns":[83],"variability":[85],"realisation":[88],"are":[89],"replicated":[90],"annotations,":[94],"closely":[96],"follow":[97],"those":[98],"manual":[100],"annotations.":[101],"These":[102],"results":[103],"potential":[106],"processing":[118],"corpus":[121],"enabling":[123],"researchers":[124],"'scale-up'":[126],"scope":[128],"relative":[133],"ease.":[134]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
