{"id":"https://openalex.org/W4391021769","doi":"https://doi.org/10.1109/asru57964.2023.10389771","title":"Unconstrained Dysfluency Modeling for Dysfluent Speech Transcription and Detection","display_name":"Unconstrained Dysfluency Modeling for Dysfluent Speech Transcription and Detection","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021769","doi":"https://doi.org/10.1109/asru57964.2023.10389771","pmid":"https://pubmed.ncbi.nlm.nih.gov/40625646"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/PMC12233912/pdf/nihms-2089704.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108846913","display_name":"Jiachen Lian","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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"]}],"countries":["US"],"is_corresponding":true,"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":"middle","author":{"id":"https://openalex.org/A5100583053","display_name":"Carly Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carly Feng","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093557706","display_name":"Naasir Farooqi","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":"Naasir Farooqi","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/A5110604838","display_name":"Steve Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steve Li","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055920361","display_name":"Anshul Kashyap","orcid":"https://orcid.org/0000-0002-1599-3178"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshul Kashyap","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/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/A5081837203","display_name":"Peter Wu","orcid":"https://orcid.org/0000-0001-6503-3936"},"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":"Peter Wu","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/A5093557707","display_name":"Robbie Netzorg","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":"Robbie Netzorg","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/A5054695986","display_name":"Tingle Li","orcid":"https://orcid.org/0000-0003-1654-8030"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tingle Li","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/A5068922218","display_name":"Gopala K. Anumanchipalli","orcid":"https://orcid.org/0000-0002-9714-7740"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopala Krishna 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":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5108846913"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":1.3341,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85109063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"2023","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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/transcription","display_name":"Transcription (linguistics)","score":0.6978287696838379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.579206109046936},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.5041981935501099},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5004012584686279},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47526687383651733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3907988667488098},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3376510739326477},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3341653347015381},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2931414246559143},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13029909133911133},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.10549551248550415},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09929153323173523}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6978287696838379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.579206109046936},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.5041981935501099},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5004012584686279},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47526687383651733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3907988667488098},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3376510739326477},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3341653347015381},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2931414246559143},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13029909133911133},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.10549551248550415},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09929153323173523},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru57964.2023.10389771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmid:40625646","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40625646","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":"Proceedings. IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12233912","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12233912","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12233912/pdf/nihms-2089704.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Workshop Autom Speech Recognit Underst","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:12233912","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12233912","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12233912/pdf/nihms-2089704.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Workshop Autom Speech Recognit Underst","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391021769.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1573083250","https://openalex.org/W1891932247","https://openalex.org/W2029812037","https://openalex.org/W2145410271","https://openalex.org/W2168510624","https://openalex.org/W2747874407","https://openalex.org/W2768920018","https://openalex.org/W2993334576","https://openalex.org/W2998572311","https://openalex.org/W3043783436","https://openalex.org/W3097777922","https://openalex.org/W3198298452","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221147660","https://openalex.org/W4223430326","https://openalex.org/W4224932945","https://openalex.org/W4225329057","https://openalex.org/W4280552695","https://openalex.org/W4296068429","https://openalex.org/W4319862440","https://openalex.org/W4323066695","https://openalex.org/W4372260274","https://openalex.org/W4372340876","https://openalex.org/W4377130946","https://openalex.org/W4378105483","https://openalex.org/W4381827575","https://openalex.org/W4382371192","https://openalex.org/W4385822293","https://openalex.org/W4385822647","https://openalex.org/W4385823207","https://openalex.org/W4391021811","https://openalex.org/W6634147634","https://openalex.org/W6772349387","https://openalex.org/W6810467415","https://openalex.org/W6847363464","https://openalex.org/W6848194691","https://openalex.org/W6849786779","https://openalex.org/W6850218400","https://openalex.org/W6852909395","https://openalex.org/W6853249747","https://openalex.org/W6853998256"],"related_works":["https://openalex.org/W2621258238","https://openalex.org/W2132470403","https://openalex.org/W2745284343","https://openalex.org/W2155576284","https://openalex.org/W2795856091","https://openalex.org/W2183463807","https://openalex.org/W175816486","https://openalex.org/W4388911376","https://openalex.org/W1645385592","https://openalex.org/W2028097510"],"abstract_inverted_index":{"Dysfluent":[0],"speech":[1],"modeling":[2,19,43],"requires":[3],"time-accurate":[4],"and":[5,12,27,50,55,98,107],"silence-aware":[6],"transcription":[7,24,49,106],"at":[8],"both":[9,48,105],"the":[10,28,60,85,96],"word-level":[11],"phonetic-level.":[13],"However,":[14],"current":[15],"research":[16],"in":[17,52,89,104],"dysfluency":[18,42],"primarily":[20],"focuses":[21],"on":[22],"either":[23],"or":[25],"detection,":[26],"performance":[29],"of":[30,87,100],"each":[31],"aspect":[32],"remains":[33],"limited.":[34],"In":[35],"this":[36],"work,":[37],"we":[38,72],"present":[39],"an":[40,53],"unconstrained":[41],"(UDM)":[44],"approach":[45],"that":[46],"addresses":[47],"detection":[51,108],"automatic":[54],"hierarchical":[56],"manner.":[57],"UDM":[58,88],"eliminates":[59],"need":[61],"for":[62],"extensive":[63],"manual":[64],"annotation":[65],"by":[66],"providing":[67],"a":[68,74],"comprehensive":[69],"solution.":[70],"Furthermore,":[71],"introduce":[73],"simulated":[75],"dysfluent":[76],"dataset":[77],"called":[78],"VCTK":[79],"<sup":[80],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[81],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">++</sup>":[82],"to":[83],"enhance":[84],"capabilities":[86],"phonetic":[90],"transcription.":[91],"Our":[92],"experimental":[93],"results":[94],"demonstrate":[95],"effectiveness":[97],"robustness":[99],"our":[101],"proposed":[102],"methods":[103],"tasks.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}
