Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202072801> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3202072801 abstract "Alzheimer's disease (AD) is a progressive neurodegenerative disease and recently attracts extensive attention worldwide. Speech technology is considered a promising solution for the early diagnosis of AD and has been enthusiastically studied. Most recent works concentrate on the use of advanced BERT-like classifiers for AD detection. Input to these classifiers are speech transcripts produced by automatic speech recognition (ASR) models. The major challenge is that the quality of transcription could degrade significantly under complex acoustic conditions in the real world. The detection performance, in consequence, is largely limited. This paper tackles the problem via tailoring and adapting pre-trained neural-network based ASR model for the downstream AD recognition task. Only bottom layers of the ASR model are retained. A simple fully-connected neural network is added on top of the tailored ASR model for classification. The heavy BERT classifier is discarded. The resulting model is light-weight and can be fine-tuned in an end-to-end manner for AD recognition. Our proposed approach takes only raw speech as input, and no extra transcription process is required. The linguistic information of speech is implicitly encoded in the tailored ASR model and contributes to boosting the performance. Experiments show that our proposed approach outperforms the best manual transcript-based RoBERTa by an absolute margin of 4.6% in terms of accuracy. Our best-performing models achieve the accuracy of 83.2% and 78.0% in the long-audio and short-audio competition tracks of the 2021 NCMMSC Alzheimer's Disease Recognition Challenge, respectively." @default.
- W3202072801 created "2021-10-11" @default.
- W3202072801 creator A5001795601 @default.
- W3202072801 creator A5013250925 @default.
- W3202072801 creator A5031989308 @default.
- W3202072801 creator A5038385200 @default.
- W3202072801 creator A5051088560 @default.
- W3202072801 creator A5071037763 @default.
- W3202072801 creator A5075223216 @default.
- W3202072801 date "2021-10-04" @default.
- W3202072801 modified "2023-10-18" @default.
- W3202072801 title "Exploiting Pre-Trained ASR Models for Alzheimer's Disease Recognition Through Spontaneous Speech" @default.
- W3202072801 cites W147964346 @default.
- W3202072801 cites W1853705225 @default.
- W3202072801 cites W1965740658 @default.
- W3202072801 cites W2085662862 @default.
- W3202072801 cites W2158516192 @default.
- W3202072801 cites W2239141610 @default.
- W3202072801 cites W2407894931 @default.
- W3202072801 cites W2597672453 @default.
- W3202072801 cites W2808631503 @default.
- W3202072801 cites W2889048668 @default.
- W3202072801 cites W2889320648 @default.
- W3202072801 cites W2891147667 @default.
- W3202072801 cites W2901101348 @default.
- W3202072801 cites W2963242190 @default.
- W3202072801 cites W2963341956 @default.
- W3202072801 cites W2965373594 @default.
- W3202072801 cites W2979979079 @default.
- W3202072801 cites W2991435809 @default.
- W3202072801 cites W2995929068 @default.
- W3202072801 cites W3015598461 @default.
- W3202072801 cites W3016010032 @default.
- W3202072801 cites W3024869864 @default.
- W3202072801 cites W3036601975 @default.
- W3202072801 cites W3037057938 @default.
- W3202072801 cites W3094848124 @default.
- W3202072801 cites W3096912371 @default.
- W3202072801 cites W3097109903 @default.
- W3202072801 cites W3097288651 @default.
- W3202072801 cites W3097533615 @default.
- W3202072801 cites W3098824823 @default.
- W3202072801 cites W3099782249 @default.
- W3202072801 cites W3161873458 @default.
- W3202072801 cites W3163826605 @default.
- W3202072801 cites W3198116506 @default.
- W3202072801 cites W3198521429 @default.
- W3202072801 cites W3198786495 @default.
- W3202072801 cites W3210120707 @default.
- W3202072801 doi "https://doi.org/10.48550/arxiv.2110.01493" @default.
- W3202072801 hasPublicationYear "2021" @default.
- W3202072801 type Work @default.
- W3202072801 sameAs 3202072801 @default.
- W3202072801 citedByCount "0" @default.
- W3202072801 crossrefType "posted-content" @default.
- W3202072801 hasAuthorship W3202072801A5001795601 @default.
- W3202072801 hasAuthorship W3202072801A5013250925 @default.
- W3202072801 hasAuthorship W3202072801A5031989308 @default.
- W3202072801 hasAuthorship W3202072801A5038385200 @default.
- W3202072801 hasAuthorship W3202072801A5051088560 @default.
- W3202072801 hasAuthorship W3202072801A5071037763 @default.
- W3202072801 hasAuthorship W3202072801A5075223216 @default.
- W3202072801 hasBestOaLocation W32020728011 @default.
- W3202072801 hasConcept C138885662 @default.
- W3202072801 hasConcept C154945302 @default.
- W3202072801 hasConcept C179926584 @default.
- W3202072801 hasConcept C28490314 @default.
- W3202072801 hasConcept C2984842247 @default.
- W3202072801 hasConcept C41008148 @default.
- W3202072801 hasConcept C41895202 @default.
- W3202072801 hasConcept C46686674 @default.
- W3202072801 hasConcept C50644808 @default.
- W3202072801 hasConcept C95623464 @default.
- W3202072801 hasConceptScore W3202072801C138885662 @default.
- W3202072801 hasConceptScore W3202072801C154945302 @default.
- W3202072801 hasConceptScore W3202072801C179926584 @default.
- W3202072801 hasConceptScore W3202072801C28490314 @default.
- W3202072801 hasConceptScore W3202072801C2984842247 @default.
- W3202072801 hasConceptScore W3202072801C41008148 @default.
- W3202072801 hasConceptScore W3202072801C41895202 @default.
- W3202072801 hasConceptScore W3202072801C46686674 @default.
- W3202072801 hasConceptScore W3202072801C50644808 @default.
- W3202072801 hasConceptScore W3202072801C95623464 @default.
- W3202072801 hasLocation W32020728011 @default.
- W3202072801 hasOpenAccess W3202072801 @default.
- W3202072801 hasPrimaryLocation W32020728011 @default.
- W3202072801 hasRelatedWork W1492933470 @default.
- W3202072801 hasRelatedWork W2025591016 @default.
- W3202072801 hasRelatedWork W2089408365 @default.
- W3202072801 hasRelatedWork W2104840956 @default.
- W3202072801 hasRelatedWork W2141727012 @default.
- W3202072801 hasRelatedWork W2944309180 @default.
- W3202072801 hasRelatedWork W4200023151 @default.
- W3202072801 hasRelatedWork W4220994654 @default.
- W3202072801 hasRelatedWork W4225852842 @default.
- W3202072801 hasRelatedWork W4309353705 @default.
- W3202072801 isParatext "false" @default.
- W3202072801 isRetracted "false" @default.
- W3202072801 magId "3202072801" @default.
- W3202072801 workType "article" @default.