Matches in SemOpenAlex for { <https://semopenalex.org/work/W4302023654> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4302023654 abstract "<p>To train machine learning algorithms to predict emotional expressions in terms of arousal and valence, annotated datasets are needed. However, as different people perceive others’ emotional expressions differently, their annotations are per se subjective. For this, annotations are typically collected from multiple annotators and averaged to obtain ground-truth labels. However, when exclusively trained on this averaged ground-truth, the trained network is agnostic to the inherent subjectivity in emotional expressions. In this work, we therefore propose an end-to-end Bayesian neural network capable of being trained on a distribution of labels to also capture the subjectivity-based label uncertainty. Instead of a Gaussian, we model the label distribution using Student’s <em>t</em>-distribution, which also accounts for the number of annotations. We derive the corresponding Kullback-Leibler divergence loss and use it to train an estimator for the distribution of labels, from which the mean and uncertainty can be inferred. We validate the proposed method using two in-the-wild datasets. We show that the proposed <em>t</em>-distribution based approach achieves state-of-the-art uncertainty modeling results in speech emotion recognition, and also consistent results in cross-corpora evaluations. Furthermore, analyses reveal that the advantage of a <em>t</em>-distribution over a Gaussian grows with increasing inter-annotator correlation and a decreasing number of annotators.</p>" @default.
- W4302023654 created "2022-10-06" @default.
- W4302023654 creator A5064507749 @default.
- W4302023654 creator A5076338187 @default.
- W4302023654 creator A5087022569 @default.
- W4302023654 date "2022-10-05" @default.
- W4302023654 modified "2023-10-09" @default.
- W4302023654 title "End-to-End Label Uncertainty Modeling in Speech Emotion Recognition using Bayesian Neural Networks and Label Distribution Learning" @default.
- W4302023654 doi "https://doi.org/10.36227/techrxiv.21252693" @default.
- W4302023654 hasPublicationYear "2022" @default.
- W4302023654 type Work @default.
- W4302023654 citedByCount "0" @default.
- W4302023654 crossrefType "posted-content" @default.
- W4302023654 hasAuthorship W4302023654A5064507749 @default.
- W4302023654 hasAuthorship W4302023654A5076338187 @default.
- W4302023654 hasAuthorship W4302023654A5087022569 @default.
- W4302023654 hasBestOaLocation W43020236541 @default.
- W4302023654 hasConcept C105795698 @default.
- W4302023654 hasConcept C107673813 @default.
- W4302023654 hasConcept C119857082 @default.
- W4302023654 hasConcept C121332964 @default.
- W4302023654 hasConcept C138885662 @default.
- W4302023654 hasConcept C146849305 @default.
- W4302023654 hasConcept C153180895 @default.
- W4302023654 hasConcept C154945302 @default.
- W4302023654 hasConcept C163716315 @default.
- W4302023654 hasConcept C171752962 @default.
- W4302023654 hasConcept C177769412 @default.
- W4302023654 hasConcept C185429906 @default.
- W4302023654 hasConcept C207390915 @default.
- W4302023654 hasConcept C28490314 @default.
- W4302023654 hasConcept C2984842247 @default.
- W4302023654 hasConcept C33923547 @default.
- W4302023654 hasConcept C41008148 @default.
- W4302023654 hasConcept C41895202 @default.
- W4302023654 hasConcept C50644808 @default.
- W4302023654 hasConcept C62520636 @default.
- W4302023654 hasConceptScore W4302023654C105795698 @default.
- W4302023654 hasConceptScore W4302023654C107673813 @default.
- W4302023654 hasConceptScore W4302023654C119857082 @default.
- W4302023654 hasConceptScore W4302023654C121332964 @default.
- W4302023654 hasConceptScore W4302023654C138885662 @default.
- W4302023654 hasConceptScore W4302023654C146849305 @default.
- W4302023654 hasConceptScore W4302023654C153180895 @default.
- W4302023654 hasConceptScore W4302023654C154945302 @default.
- W4302023654 hasConceptScore W4302023654C163716315 @default.
- W4302023654 hasConceptScore W4302023654C171752962 @default.
- W4302023654 hasConceptScore W4302023654C177769412 @default.
- W4302023654 hasConceptScore W4302023654C185429906 @default.
- W4302023654 hasConceptScore W4302023654C207390915 @default.
- W4302023654 hasConceptScore W4302023654C28490314 @default.
- W4302023654 hasConceptScore W4302023654C2984842247 @default.
- W4302023654 hasConceptScore W4302023654C33923547 @default.
- W4302023654 hasConceptScore W4302023654C41008148 @default.
- W4302023654 hasConceptScore W4302023654C41895202 @default.
- W4302023654 hasConceptScore W4302023654C50644808 @default.
- W4302023654 hasConceptScore W4302023654C62520636 @default.
- W4302023654 hasLocation W43020236541 @default.
- W4302023654 hasLocation W43020236542 @default.
- W4302023654 hasOpenAccess W4302023654 @default.
- W4302023654 hasPrimaryLocation W43020236541 @default.
- W4302023654 hasRelatedWork W2070010392 @default.
- W4302023654 hasRelatedWork W2099482349 @default.
- W4302023654 hasRelatedWork W2547407901 @default.
- W4302023654 hasRelatedWork W2920644021 @default.
- W4302023654 hasRelatedWork W2963015795 @default.
- W4302023654 hasRelatedWork W3215977089 @default.
- W4302023654 hasRelatedWork W4285591196 @default.
- W4302023654 hasRelatedWork W4288481642 @default.
- W4302023654 hasRelatedWork W4301893945 @default.
- W4302023654 hasRelatedWork W4308372269 @default.
- W4302023654 isParatext "false" @default.
- W4302023654 isRetracted "false" @default.
- W4302023654 workType "article" @default.