FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225535697> ?p ?o ?g. }

• W4225535697 endingPage "1030" @default.
• W4225535697 startingPage "1018" @default.
• W4225535697 abstract "Machine learning (ML) approaches show increasing promise in their ability to identify vocal markers of autism. Nonetheless, it is unclear to what extent such markers generalize to new speech samples collected, for example, using a different speech task or in a different language. In this paper, we systematically assess the generalizability of ML findings across a variety of contexts. We train promising published ML models of vocal markers of autism on novel cross-linguistic datasets following a rigorous pipeline to minimize overfitting, including cross-validated training and ensemble models. We test the generalizability of the models by testing them on (i) different participants from the same study, performing the same task; (ii) the same participants, performing a different (but similar) task; (iii) a different study with participants speaking a different language, performing the same type of task. While model performance is similar to previously published findings when trained and tested on data from the same study (out-of-sample performance), there is considerable variance between studies. Crucially, the models do not generalize well to different, though similar, tasks and not at all to new languages. The ML pipeline is openly shared. Generalizability of ML models of vocal markers of autism is an issue. We outline three recommendations for strategies researchers could take to be more explicit about generalizability and improve it in future studies. LAY SUMMARY: Machine learning approaches promise to be able to identify autism from voice only. These models underestimate how diverse the contexts in which we speak are, how diverse the languages used are and how diverse autistic voices are. Machine learning approaches need to be more careful in defining their limits and generalizability." @default.
• W4225535697 created "2022-05-05" @default.
• W4225535697 creator A5001006068 @default.
• W4225535697 creator A5005248895 @default.
• W4225535697 creator A5008159289 @default.
• W4225535697 creator A5018733566 @default.
• W4225535697 creator A5032082404 @default.
• W4225535697 creator A5043047142 @default.
• W4225535697 creator A5046527916 @default.
• W4225535697 creator A5054844385 @default.
• W4225535697 creator A5083510283 @default.
• W4225535697 creator A5088113286 @default.
• W4225535697 creator A5088387026 @default.
• W4225535697 date "2022-04-06" @default.
• W4225535697 modified "2023-10-02" @default.
• W4225535697 title "Vocal markers of autism: Assessing the generalizability of machine learning models" @default.
• W4225535697 cites W103102414 @default.
• W4225535697 cites W1974560241 @default.
• W4225535697 cites W1989643076 @default.
• W4225535697 cites W2023238480 @default.
• W4225535697 cites W2025661842 @default.
• W4225535697 cites W2049577872 @default.
• W4225535697 cites W2085662862 @default.
• W4225535697 cites W2116810060 @default.
• W4225535697 cites W2120064584 @default.
• W4225535697 cites W2158392329 @default.
• W4225535697 cites W2182764510 @default.
• W4225535697 cites W2239141610 @default.
• W4225535697 cites W2339367962 @default.
• W4225535697 cites W2598207902 @default.
• W4225535697 cites W2751778071 @default.
• W4225535697 cites W2790046776 @default.
• W4225535697 cites W2794726578 @default.
• W4225535697 cites W2896464508 @default.
• W4225535697 cites W2940437698 @default.
• W4225535697 cites W2945020349 @default.
• W4225535697 cites W2951540548 @default.
• W4225535697 cites W2952790857 @default.
• W4225535697 cites W2973049979 @default.
• W4225535697 cites W2981675185 @default.
• W4225535697 cites W2989852193 @default.
• W4225535697 cites W2995752917 @default.
• W4225535697 cites W3004047823 @default.
• W4225535697 cites W3009329175 @default.
• W4225535697 cites W3010004490 @default.
• W4225535697 cites W3015636347 @default.
• W4225535697 cites W3016166616 @default.
• W4225535697 cites W3026904087 @default.
• W4225535697 cites W3041256490 @default.
• W4225535697 cites W3101840241 @default.
• W4225535697 cites W3110175868 @default.
• W4225535697 cites W3136916374 @default.
• W4225535697 cites W3148933250 @default.
• W4225535697 cites W3170561227 @default.
• W4225535697 cites W3198049450 @default.
• W4225535697 cites W3208504364 @default.
• W4225535697 cites W4200142301 @default.
• W4225535697 cites W4211209158 @default.
• W4225535697 cites W4239301040 @default.
• W4225535697 cites W4243072198 @default.
• W4225535697 cites W4247028317 @default.
• W4225535697 cites W429766147 @default.
• W4225535697 doi "https://doi.org/10.1002/aur.2721" @default.
• W4225535697 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35385224" @default.
• W4225535697 hasPublicationYear "2022" @default.
• W4225535697 type Work @default.
• W4225535697 citedByCount "9" @default.
• W4225535697 countsByYear W42255356972022 @default.
• W4225535697 countsByYear W42255356972023 @default.
• W4225535697 crossrefType "journal-article" @default.
• W4225535697 hasAuthorship W4225535697A5001006068 @default.
• W4225535697 hasAuthorship W4225535697A5005248895 @default.
• W4225535697 hasAuthorship W4225535697A5008159289 @default.
• W4225535697 hasAuthorship W4225535697A5018733566 @default.
• W4225535697 hasAuthorship W4225535697A5032082404 @default.
• W4225535697 hasAuthorship W4225535697A5043047142 @default.
• W4225535697 hasAuthorship W4225535697A5046527916 @default.
• W4225535697 hasAuthorship W4225535697A5054844385 @default.
• W4225535697 hasAuthorship W4225535697A5083510283 @default.
• W4225535697 hasAuthorship W4225535697A5088113286 @default.
• W4225535697 hasAuthorship W4225535697A5088387026 @default.
• W4225535697 hasBestOaLocation W42255356972 @default.
• W4225535697 hasConcept C119857082 @default.
• W4225535697 hasConcept C121955636 @default.
• W4225535697 hasConcept C134306372 @default.
• W4225535697 hasConcept C138496976 @default.
• W4225535697 hasConcept C144133560 @default.
• W4225535697 hasConcept C154945302 @default.
• W4225535697 hasConcept C15744967 @default.
• W4225535697 hasConcept C162324750 @default.
• W4225535697 hasConcept C177148314 @default.
• W4225535697 hasConcept C180747234 @default.
• W4225535697 hasConcept C187736073 @default.
• W4225535697 hasConcept C196083921 @default.
• W4225535697 hasConcept C199360897 @default.
• W4225535697 hasConcept C204321447 @default.
• W4225535697 hasConcept C205778803 @default.
• W4225535697 hasConcept C22019652 @default.

• next