Matches in SemOpenAlex for { <https://semopenalex.org/work/W3106506544> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3106506544 abstract "Speech emotion recognition is an important aspect of human-computer interaction. Prior work proposes various end-to-end models to improve the classification performance. However, most of them rely on the cross-entropy loss together with softmax as the supervision component, which does not explicitly encourage discriminative learning of features. In this paper, we introduce the contrastive loss function to encourage intra-class compactness and inter-class separability between learnable features. Furthermore, multiple feature selection methods and pairwise sample selection methods are evaluated. To verify the performance of the proposed system, we conduct experiments on The Interactive Emotional Dyadic Motion Capture (IEMOCAP) database, a common evaluation corpus. Experimental results reveal the advantages of the proposed method, which reaches 62.19% in the weighted accuracy and 63.21% in the unweighted accuracy. It outperforms the baseline system that is optimized without the contrastive loss function with 1.14% and 2.55% in the weighted accuracy and the unweighted accuracy, respectively." @default.
- W3106506544 created "2020-11-23" @default.
- W3106506544 creator A5001973434 @default.
- W3106506544 creator A5017193282 @default.
- W3106506544 creator A5062854541 @default.
- W3106506544 creator A5071074705 @default.
- W3106506544 date "2018-10-19" @default.
- W3106506544 modified "2023-09-26" @default.
- W3106506544 title "Speech Emotion Recognition via Contrastive Loss under Siamese Networks" @default.
- W3106506544 cites W1902237438 @default.
- W3106506544 cites W2016661008 @default.
- W3106506544 cites W2055332436 @default.
- W3106506544 cites W2099767163 @default.
- W3106506544 cites W2146334809 @default.
- W3106506544 cites W2157364932 @default.
- W3106506544 cites W2191779130 @default.
- W3106506544 cites W2214134199 @default.
- W3106506544 cites W2343758848 @default.
- W3106506544 cites W2512449761 @default.
- W3106506544 cites W2512885694 @default.
- W3106506544 cites W2747172199 @default.
- W3106506544 cites W2747664154 @default.
- W3106506544 cites W2962736520 @default.
- W3106506544 cites W2963467407 @default.
- W3106506544 doi "https://doi.org/10.1145/3267935.3267946" @default.
- W3106506544 hasPublicationYear "2018" @default.
- W3106506544 type Work @default.
- W3106506544 sameAs 3106506544 @default.
- W3106506544 citedByCount "34" @default.
- W3106506544 countsByYear W31065065442019 @default.
- W3106506544 countsByYear W31065065442020 @default.
- W3106506544 countsByYear W31065065442021 @default.
- W3106506544 countsByYear W31065065442022 @default.
- W3106506544 countsByYear W31065065442023 @default.
- W3106506544 crossrefType "proceedings-article" @default.
- W3106506544 hasAuthorship W3106506544A5001973434 @default.
- W3106506544 hasAuthorship W3106506544A5017193282 @default.
- W3106506544 hasAuthorship W3106506544A5062854541 @default.
- W3106506544 hasAuthorship W3106506544A5071074705 @default.
- W3106506544 hasBestOaLocation W31065065442 @default.
- W3106506544 hasConcept C119857082 @default.
- W3106506544 hasConcept C148483581 @default.
- W3106506544 hasConcept C153180895 @default.
- W3106506544 hasConcept C154945302 @default.
- W3106506544 hasConcept C167981619 @default.
- W3106506544 hasConcept C184898388 @default.
- W3106506544 hasConcept C188441871 @default.
- W3106506544 hasConcept C2777438025 @default.
- W3106506544 hasConcept C28490314 @default.
- W3106506544 hasConcept C41008148 @default.
- W3106506544 hasConcept C50644808 @default.
- W3106506544 hasConcept C52622490 @default.
- W3106506544 hasConcept C97931131 @default.
- W3106506544 hasConceptScore W3106506544C119857082 @default.
- W3106506544 hasConceptScore W3106506544C148483581 @default.
- W3106506544 hasConceptScore W3106506544C153180895 @default.
- W3106506544 hasConceptScore W3106506544C154945302 @default.
- W3106506544 hasConceptScore W3106506544C167981619 @default.
- W3106506544 hasConceptScore W3106506544C184898388 @default.
- W3106506544 hasConceptScore W3106506544C188441871 @default.
- W3106506544 hasConceptScore W3106506544C2777438025 @default.
- W3106506544 hasConceptScore W3106506544C28490314 @default.
- W3106506544 hasConceptScore W3106506544C41008148 @default.
- W3106506544 hasConceptScore W3106506544C50644808 @default.
- W3106506544 hasConceptScore W3106506544C52622490 @default.
- W3106506544 hasConceptScore W3106506544C97931131 @default.
- W3106506544 hasLocation W31065065441 @default.
- W3106506544 hasLocation W31065065442 @default.
- W3106506544 hasOpenAccess W3106506544 @default.
- W3106506544 hasPrimaryLocation W31065065441 @default.
- W3106506544 hasRelatedWork W1982774199 @default.
- W3106506544 hasRelatedWork W2067451062 @default.
- W3106506544 hasRelatedWork W2111662190 @default.
- W3106506544 hasRelatedWork W2203956467 @default.
- W3106506544 hasRelatedWork W2601105035 @default.
- W3106506544 hasRelatedWork W2743258233 @default.
- W3106506544 hasRelatedWork W2963480192 @default.
- W3106506544 hasRelatedWork W3013493337 @default.
- W3106506544 hasRelatedWork W3024646494 @default.
- W3106506544 hasRelatedWork W3106506544 @default.
- W3106506544 isParatext "false" @default.
- W3106506544 isRetracted "false" @default.
- W3106506544 magId "3106506544" @default.
- W3106506544 workType "article" @default.