Matches in SemOpenAlex for { <https://semopenalex.org/work/W2798632413> ?p ?o ?g. }
- W2798632413 abstract "The performance of speech emotion recognition is affected by the differences in data distributions between train (source domain) and test (target domain) sets used to build and evaluate the models. This is a common problem, as multiple studies have shown that the performance of emotional classifiers drop when they are exposed to data that does not match the distribution used to build the emotion classifiers. The difference in data distributions becomes very clear when the training and testing data come from different domains, causing a large performance gap between validation and testing performance. Due to the high cost of annotating new data and the abundance of unlabeled data, it is crucial to extract as much useful information as possible from the available unlabeled data. This study looks into the use of adversarial multitask training to extract a common representation between train and test domains. The primary task is to predict emotional attribute-based descriptors for arousal, valence, or dominance. The secondary task is to learn a common representation where the train and test domains cannot be distinguished. By using a gradient reversal layer, the gradients coming from the domain classifier are used to bring the source and target domain representations closer. We show that exploiting unlabeled data consistently leads to better emotion recognition performance across all emotional dimensions. We visualize the effect of adversarial training on the feature representation across the proposed deep learning architecture. The analysis shows that the data representations for the train and test domains converge as the data is passed to deeper layers of the network. We also evaluate the difference in performance when we use a shallow neural network versus a emph{deep neural network} (DNN) and the effect of the number of shared layers used by the task and domain classifiers." @default.
- W2798632413 created "2018-05-07" @default.
- W2798632413 creator A5016915412 @default.
- W2798632413 creator A5040793194 @default.
- W2798632413 date "2018-04-20" @default.
- W2798632413 modified "2023-09-27" @default.
- W2798632413 title "Domain Adversarial for Acoustic Emotion Recognition" @default.
- W2798632413 cites W1581984155 @default.
- W2798632413 cites W1608705073 @default.
- W2798632413 cites W1731081199 @default.
- W2798632413 cites W2016839396 @default.
- W2798632413 cites W2071712938 @default.
- W2798632413 cites W2085662862 @default.
- W2798632413 cites W2113087918 @default.
- W2798632413 cites W2125462608 @default.
- W2798632413 cites W2129794709 @default.
- W2798632413 cites W2135195345 @default.
- W2798632413 cites W2146334809 @default.
- W2798632413 cites W2170967251 @default.
- W2798632413 cites W22861983 @default.
- W2798632413 cites W2322208196 @default.
- W2798632413 cites W2342475039 @default.
- W2798632413 cites W2399478587 @default.
- W2798632413 cites W2404863510 @default.
- W2798632413 cites W2407346284 @default.
- W2798632413 cites W2503045345 @default.
- W2798632413 cites W2510867321 @default.
- W2798632413 cites W2525412388 @default.
- W2798632413 cites W2589599921 @default.
- W2798632413 cites W2632855849 @default.
- W2798632413 cites W2661967629 @default.
- W2798632413 cites W2680534654 @default.
- W2798632413 cites W2742542661 @default.
- W2798632413 cites W2747172199 @default.
- W2798632413 cites W2903382683 @default.
- W2798632413 cites W2953384591 @default.
- W2798632413 cites W2963569749 @default.
- W2798632413 hasPublicationYear "2018" @default.
- W2798632413 type Work @default.
- W2798632413 sameAs 2798632413 @default.
- W2798632413 citedByCount "1" @default.
- W2798632413 countsByYear W27986324132019 @default.
- W2798632413 crossrefType "posted-content" @default.
- W2798632413 hasAuthorship W2798632413A5016915412 @default.
- W2798632413 hasAuthorship W2798632413A5040793194 @default.
- W2798632413 hasConcept C119857082 @default.
- W2798632413 hasConcept C138885662 @default.
- W2798632413 hasConcept C153180895 @default.
- W2798632413 hasConcept C154945302 @default.
- W2798632413 hasConcept C162324750 @default.
- W2798632413 hasConcept C16910744 @default.
- W2798632413 hasConcept C17744445 @default.
- W2798632413 hasConcept C187736073 @default.
- W2798632413 hasConcept C199360897 @default.
- W2798632413 hasConcept C199539241 @default.
- W2798632413 hasConcept C2776145971 @default.
- W2798632413 hasConcept C2776359362 @default.
- W2798632413 hasConcept C2776401178 @default.
- W2798632413 hasConcept C2780451532 @default.
- W2798632413 hasConcept C28006648 @default.
- W2798632413 hasConcept C28490314 @default.
- W2798632413 hasConcept C37736160 @default.
- W2798632413 hasConcept C41008148 @default.
- W2798632413 hasConcept C41895202 @default.
- W2798632413 hasConcept C59404180 @default.
- W2798632413 hasConcept C94625758 @default.
- W2798632413 hasConcept C95623464 @default.
- W2798632413 hasConceptScore W2798632413C119857082 @default.
- W2798632413 hasConceptScore W2798632413C138885662 @default.
- W2798632413 hasConceptScore W2798632413C153180895 @default.
- W2798632413 hasConceptScore W2798632413C154945302 @default.
- W2798632413 hasConceptScore W2798632413C162324750 @default.
- W2798632413 hasConceptScore W2798632413C16910744 @default.
- W2798632413 hasConceptScore W2798632413C17744445 @default.
- W2798632413 hasConceptScore W2798632413C187736073 @default.
- W2798632413 hasConceptScore W2798632413C199360897 @default.
- W2798632413 hasConceptScore W2798632413C199539241 @default.
- W2798632413 hasConceptScore W2798632413C2776145971 @default.
- W2798632413 hasConceptScore W2798632413C2776359362 @default.
- W2798632413 hasConceptScore W2798632413C2776401178 @default.
- W2798632413 hasConceptScore W2798632413C2780451532 @default.
- W2798632413 hasConceptScore W2798632413C28006648 @default.
- W2798632413 hasConceptScore W2798632413C28490314 @default.
- W2798632413 hasConceptScore W2798632413C37736160 @default.
- W2798632413 hasConceptScore W2798632413C41008148 @default.
- W2798632413 hasConceptScore W2798632413C41895202 @default.
- W2798632413 hasConceptScore W2798632413C59404180 @default.
- W2798632413 hasConceptScore W2798632413C94625758 @default.
- W2798632413 hasConceptScore W2798632413C95623464 @default.
- W2798632413 hasLocation W27986324131 @default.
- W2798632413 hasOpenAccess W2798632413 @default.
- W2798632413 hasPrimaryLocation W27986324131 @default.
- W2798632413 hasRelatedWork W1731081199 @default.
- W2798632413 hasRelatedWork W2727070910 @default.
- W2798632413 hasRelatedWork W2758584002 @default.
- W2798632413 hasRelatedWork W2794887779 @default.
- W2798632413 hasRelatedWork W2896591327 @default.
- W2798632413 hasRelatedWork W2902318025 @default.
- W2798632413 hasRelatedWork W2944025081 @default.
- W2798632413 hasRelatedWork W2944379307 @default.