{"id":"https://openalex.org/W7224086596","doi":"https://doi.org/10.5281/zenodo.23734381","title":"Robust Automatic Stuttering Detection Through Multi-Domain Feature Learning and Attention-Based Classification","display_name":"Robust Automatic Stuttering Detection Through Multi-Domain Feature Learning and Attention-Based Classification","publication_year":2026,"publication_date":"2026-10-28","ids":{"openalex":"https://openalex.org/W7224086596","doi":"https://doi.org/10.5281/zenodo.23734381"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23734381","doi":"https://doi.org/10.5281/zenodo.23734381","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23734381","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"volume":null,"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23734381","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160017750","display_name":"G Seshikala Kusuma H R","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kusuma H R, G Seshikala","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160017750"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8749365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.6273999810218811,"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":0.6273999810218811,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.322299987077713,"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/T10863","display_name":"Voice and Speech Disorders","score":0.03060000017285347,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology (medical)"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stuttering-detection","display_name":"stuttering detection","score":0.9390000104904175},{"id":"https://openalex.org/keywords/repetition","display_name":"repetition","score":0.6940000057220459},{"id":"https://openalex.org/keywords/prolongation","display_name":"prolongation","score":0.9869999885559082},{"id":"https://openalex.org/keywords/blocks","display_name":"blocks","score":0.7419999837875366},{"id":"https://openalex.org/keywords/interjections","display_name":"interjections","score":0.9700000286102295},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.6579999923706055},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.8050000071525574},{"id":"https://openalex.org/keywords/multi-domain-feature-extraction","display_name":"multi-domain feature extraction","score":0.7680000066757202},{"id":"https://openalex.org/keywords/wav2vec-2-0","display_name":"wav2vec 2.0","score":0.8790000081062317},{"id":"https://openalex.org/keywords/contextual-features","display_name":"contextual features","score":0.5569999814033508},{"id":"https://openalex.org/keywords/spectral-properties","display_name":"spectral properties","score":0.5080000162124634},{"id":"https://openalex.org/keywords/zero-crossing-rate","display_name":"zero-crossing rate","score":0.7120000123977661},{"id":"https://openalex.org/keywords/spectral-flux","display_name":"spectral flux","score":0.6700000166893005},{"id":"https://openalex.org/keywords/pitch-features","display_name":"pitch features","score":0.4560000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804999947547913},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7038000226020813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6582000255584717},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5983999967575073},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5641999840736389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5504000186920166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5432000160217285},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4781000018119812},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.40610000491142273},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.34630000591278076},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2524999976158142},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23734381","doi":"https://doi.org/10.5281/zenodo.23734381","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23734381","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.5281/zenodo.23734382","doi":"https://doi.org/10.5281/zenodo.23734382","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23734382","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23734381","doi":"https://doi.org/10.5281/zenodo.23734381","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23734381","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7223820158","https://openalex.org/W7203622564","https://openalex.org/W7196948477","https://openalex.org/W7162990735","https://openalex.org/W4281909602","https://openalex.org/W4403525704","https://openalex.org/W4386996915","https://openalex.org/W2981902467","https://openalex.org/W3198298452","https://openalex.org/W3089186772"],"abstract_inverted_index":{"Automatic":[0],"detection":[1,38,265],"of":[2,11,14,41,74,101,129,150,182,196,223,254],"speech":[3,20,42,156,263,268],"disfluencies,":[4,43],"particularly":[5],"stuttering,":[6],"remains":[7],"a":[8,31,245],"challenge":[9],"because":[10],"the":[12,56,66,91,99,106,110,122,127,130,138,148,151,173,191,221,236,252,255],"variability":[13],"disfluency":[15,264],"patterns,":[16],"limited":[17],"annotated":[18],"pathological":[19],"data,":[21],"class":[22],"imbalance,":[23],"and":[24,39,49,71,85,144,180,185,199,204,208,211,232,244,260],"diverse":[25,267],"acoustic":[26],"conditions.":[27,157],"This":[28],"study":[29,218],"proposes":[30],"robust":[32,261],"deep":[33],"learning":[34],"framework":[35,54,238,257],"for":[36,201,258],"automatic":[37,262],"classification":[40],"including":[44],"repetitions,":[45,202],"prolongations,":[46,203],"blocks,":[47],"interjections,":[48],"fluent":[50],"speech.":[51,75,103],"The":[52],"proposed":[53,152,192,256],"combines":[55],"balanced":[57],"data":[58,224],"augmentation":[59],"with":[60,177,235],"multi-domain":[61],"feature":[62,108,175,227,229],"extraction":[63],"to":[64,97,125,146,170],"capture":[65],"complementary":[67],"spectral,":[68],"temporal,":[69],"pitch,":[70],"contextual":[72,86,226],"characteristics":[73],"Mel-frequency":[76],"cepstral":[77],"coefficients":[78],"(MFCCs),":[79],"zero-crossing":[80],"rate":[81],"(ZCR),":[82],"spectral":[83],"flux,":[84],"representations":[87],"are":[88,95,113],"derived":[89],"from":[90,165],"pre-trained":[92],"Wav2Vec":[93],"2.0":[94],"integrated,":[96],"improve":[98,105],"representation":[100],"disfluent":[102],"To":[104],"discriminative":[107],"learning,":[109],"extracted":[111],"features":[112],"processed":[114],"using":[115,137,167,172],"an":[116,161],"attention-based":[117],"convolutional":[118],"architecture,":[119],"while":[120],"employing":[121],"class-balancing":[123,233],"strategies":[124],"reduce":[126],"influence":[128],"dominant":[131],"fluent-speech":[132],"class.":[133],"Experiments":[134],"were":[135],"conducted":[136],"benchmark":[139],"datasets":[140],"like":[141],"UCLASS,":[142,207],"SEP-28k,":[143,214],"FluencyBank":[145],"demonstrate":[147,251],"effectiveness":[149],"approach":[153],"across":[154,266],"different":[155],"Feature-level":[158],"evaluation":[159],"shows":[160],"improvement":[162],"in":[163],"accuracy":[164,243],"82.3%":[166],"MFCCs":[168],"alone":[169],"91.2%":[171],"complete":[174,237],"set,":[176],"precision,":[178],"recall,":[179],"F1-score":[181],"0.90,":[183],"0.91,":[184,186],"respectively.":[187,215],"For":[188],"disfluency-specific":[189],"detection,":[190],"model":[193],"achieved":[194],"accuracies":[195],"95.60%,":[197],"94.50%,":[198],"60.80%":[200],"blocks":[205],"on":[206,213],"86.40%,":[209],"92.50%,":[210],"74.20%":[212],"An":[216],"ablation":[217],"further":[219],"demonstrates":[220],"contribution":[222],"augmentation,":[225],"extraction,":[228],"selection,":[230],"attention,":[231],"components,":[234],"achieving":[239],"95.10":[240],"\u00b1":[241],"0.38%":[242],"94.35%":[246],"macro":[247],"F1-score.":[248],"These":[249],"results":[250],"potential":[253],"accurate":[259],"datasets.":[269]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-29T00:00:00"}