{"id":"https://openalex.org/W4406461796","doi":"https://doi.org/10.1109/slt61566.2024.10832222","title":"Stutter-Solver: End-To-End Multi-Lingual Dysfluency Detection","display_name":"Stutter-Solver: End-To-End Multi-Lingual Dysfluency Detection","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461796","doi":"https://doi.org/10.1109/slt61566.2024.10832222","pmid":"https://pubmed.ncbi.nlm.nih.gov/40626052"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12233913/pdf/nihms-2089708.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111310995","display_name":"Xuanru Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuanru Zhou","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015390421","display_name":"Cheol Jun Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheol Jun Cho","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106916694","display_name":"Ayati Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayati Sharma","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106870223","display_name":"Brittany Morin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113384","display_name":"Universidad Cat\u00f3lica de Santa Fe","ror":"https://ror.org/02b7n7v15","country_code":"AR","type":"education","lineage":["https://openalex.org/I4210113384"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Brittany Morin","raw_affiliation_strings":["UCSF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSF","institution_ids":["https://openalex.org/I4210113384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104422190","display_name":"David Baquirin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113384","display_name":"Universidad Cat\u00f3lica de Santa Fe","ror":"https://ror.org/02b7n7v15","country_code":"AR","type":"education","lineage":["https://openalex.org/I4210113384"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"David Baquirin","raw_affiliation_strings":["UCSF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSF","institution_ids":["https://openalex.org/I4210113384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064932904","display_name":"Jet M. J. Vonk","orcid":"https://orcid.org/0000-0002-1808-8843"},"institutions":[{"id":"https://openalex.org/I4210113384","display_name":"Universidad Cat\u00f3lica de Santa Fe","ror":"https://ror.org/02b7n7v15","country_code":"AR","type":"education","lineage":["https://openalex.org/I4210113384"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Jet Vonk","raw_affiliation_strings":["UCSF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSF","institution_ids":["https://openalex.org/I4210113384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077923985","display_name":"Zoe Ezzes","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113384","display_name":"Universidad Cat\u00f3lica de Santa Fe","ror":"https://ror.org/02b7n7v15","country_code":"AR","type":"education","lineage":["https://openalex.org/I4210113384"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Zoe Ezzes","raw_affiliation_strings":["UCSF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSF","institution_ids":["https://openalex.org/I4210113384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059104887","display_name":"Zachary Miller","orcid":"https://orcid.org/0000-0002-5991-3053"},"institutions":[{"id":"https://openalex.org/I4210113384","display_name":"Universidad Cat\u00f3lica de Santa Fe","ror":"https://ror.org/02b7n7v15","country_code":"AR","type":"education","lineage":["https://openalex.org/I4210113384"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Zachary Miller","raw_affiliation_strings":["UCSF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSF","institution_ids":["https://openalex.org/I4210113384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012772846","display_name":"Boon Lead Tee","orcid":"https://orcid.org/0000-0003-2217-3466"},"institutions":[{"id":"https://openalex.org/I4210113384","display_name":"Universidad Cat\u00f3lica de Santa Fe","ror":"https://ror.org/02b7n7v15","country_code":"AR","type":"education","lineage":["https://openalex.org/I4210113384"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Boon Lead Tee","raw_affiliation_strings":["UCSF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSF","institution_ids":["https://openalex.org/I4210113384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043432683","display_name":"Maria Luisa Gorno\u2010Tempini","orcid":"https://orcid.org/0000-0002-7426-7782"},"institutions":[{"id":"https://openalex.org/I4210113384","display_name":"Universidad Cat\u00f3lica de Santa Fe","ror":"https://ror.org/02b7n7v15","country_code":"AR","type":"education","lineage":["https://openalex.org/I4210113384"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Maria Luisa Gorno-Tempini","raw_affiliation_strings":["UCSF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSF","institution_ids":["https://openalex.org/I4210113384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108846913","display_name":"Jiachen Lian","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiachen Lian","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092897580","display_name":"Gopala Anumanchipalli","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopala Anumanchipalli","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5111310995"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":2.3657,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.89138648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"2024","issue":null,"first_page":"1039","last_page":"1046"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical 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":0.9983999729156494,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.6732631921768188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.57117760181427},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5222612023353577},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.4952916204929352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.256799578666687}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6732631921768188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.57117760181427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5222612023353577},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.4952916204929352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.256799578666687},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt61566.2024.10832222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmid:40626052","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40626052","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SLT ... : ... IEEE Workshop on Spoken Language Technology : proceedings. IEEE Workshop on Spoken Language Technology","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12233913","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12233913","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12233913/pdf/nihms-2089708.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SLT Workshop Spok Lang Technol","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:12233913","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12233913","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12233913/pdf/nihms-2089708.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SLT Workshop Spok Lang Technol","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406461796.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1839011234","https://openalex.org/W2002299114","https://openalex.org/W2032423026","https://openalex.org/W2079075205","https://openalex.org/W2138190873","https://openalex.org/W2612560781","https://openalex.org/W2963037989","https://openalex.org/W2963300588","https://openalex.org/W2993334576","https://openalex.org/W2998572311","https://openalex.org/W3015764649","https://openalex.org/W3015877095","https://openalex.org/W3097777922","https://openalex.org/W3146945401","https://openalex.org/W3161639065","https://openalex.org/W3198298452","https://openalex.org/W3198533616","https://openalex.org/W4223430326","https://openalex.org/W4224932945","https://openalex.org/W4225329057","https://openalex.org/W4280552695","https://openalex.org/W4283659485","https://openalex.org/W4309395027","https://openalex.org/W4323066695","https://openalex.org/W4352981168","https://openalex.org/W4372260274","https://openalex.org/W4372337800","https://openalex.org/W4378105483","https://openalex.org/W4382371192","https://openalex.org/W4385245566","https://openalex.org/W4385823207","https://openalex.org/W4391021769","https://openalex.org/W4391021811","https://openalex.org/W4399912219","https://openalex.org/W4402115913","https://openalex.org/W6772349387","https://openalex.org/W6796464841","https://openalex.org/W6839738141","https://openalex.org/W6846936884","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6852909395","https://openalex.org/W6860818266","https://openalex.org/W6870487644","https://openalex.org/W6980117322"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W2186864281","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4404782863"],"abstract_inverted_index":{"Current":[0],"de-facto":[1],"dysfluency":[2,43,67,80,110],"modeling":[3],"methods":[4],"[1,":[5],"2]":[6],"utilize":[7],"template":[8],"matching":[9],"algorithms":[10],"which":[11],"are":[12,22,115],"not":[13,23],"generalizable":[14],"to":[15],"out-of-domain":[16],"real-world":[17],"dysfluencies":[18,89],"across":[19],"languages,":[20],"and":[21,47,62,72,84,95,99,113],"scalable":[24],"with":[25,44],"increasing":[26],"amounts":[27],"of":[28],"training":[29],"data.":[30],"To":[31,69],"handle":[32,60],"these":[33],"problems,":[34],"we":[35,75],"propose":[36],"Stutter-Solver:":[37],"an":[38],"end-toend":[39],"framework":[40],"that":[41],"detects":[42],"accurate":[45],"type":[46],"time":[48],"transcription,":[49],"inspired":[50],"by":[51],"the":[52],"YOLO":[53],"[3]":[54],"object":[55],"detection":[56],"algorithm.":[57],"Stutter-Solver":[58],"can":[59],"co-dysfluencies":[61],"is":[63],"a":[64],"natural":[65,87],"multi-lingual":[66],"detector.":[68],"leverage":[70],"scalability":[71],"boost":[73],"performance,":[74],"also":[76],"introduce":[77],"three":[78],"novel":[79],"corpora:":[81],"VCTK-Pro,":[82],"VCTK-Art,":[83],"AISHELL3-Pro,":[85],"simulating":[86],"spoken":[88],"including":[90],"repetition,":[91],"block,":[92],"missing,":[93],"replacement,":[94],"prolongation":[96],"through":[97],"articulatory-encodec":[98],"TTS-based":[100],"methods.":[101],"Our":[102],"approach":[103],"achieves":[104],"state-of-the-art":[105],"performance":[106],"on":[107],"all":[108],"available":[109],"corpora.":[111],"Code":[112],"datasets":[114],"open-sourced":[116],"at":[117],"https://github.com/eureka235/Stutter-Solver.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}