Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313854518> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4313854518 abstract "This paper presents a bimodal emotion recognition system based on the voice and text information using small amount of speech data. Specifically, speech is divided into voice and text to learn emotion classifiers for each modal. The probabilities obtained from these emotion classifiers are weighted based on Mehrabian’s rule and summed up for each emotion to calculate the final score for bimodal emotion recognition. To create a highly accurate system while solving the problem that there are few Japanese speech data with emotion labels, we propose a novel data augmentation method and employ a transfer learning approach based on a pre-trained VGG16 model and a fine-tuned Bidirectional Encoder Representations from Transformers (BERT) model on the tweets. In order to prove the effectiveness of the proposed method, we revealed the recognition results for 7 emotional states, i.e., anger, sadness, joy, fear, surprise, disgust, and neutral. The experiment result suggested that our novel data augmentation method improved the accuracy and that bimodal predictions based on voice and text-based outperformed the single-model predictions." @default.
- W4313854518 created "2023-01-10" @default.
- W4313854518 creator A5003358015 @default.
- W4313854518 creator A5004708598 @default.
- W4313854518 creator A5014470931 @default.
- W4313854518 creator A5024519127 @default.
- W4313854518 creator A5031861539 @default.
- W4313854518 creator A5084984842 @default.
- W4313854518 date "2022-12-10" @default.
- W4313854518 modified "2023-10-16" @default.
- W4313854518 title "Learning a Bimodal Emotion Recognition System Based on Small Amount of Speech Data" @default.
- W4313854518 cites W2000838212 @default.
- W4313854518 cites W2016618864 @default.
- W4313854518 cites W2085662862 @default.
- W4313854518 cites W2147068760 @default.
- W4313854518 cites W2153720647 @default.
- W4313854518 cites W2295001676 @default.
- W4313854518 cites W2493916176 @default.
- W4313854518 cites W2962739339 @default.
- W4313854518 cites W2962770129 @default.
- W4313854518 cites W2964701214 @default.
- W4313854518 cites W3197642003 @default.
- W4313854518 cites W3208220966 @default.
- W4313854518 cites W3215440557 @default.
- W4313854518 doi "https://doi.org/10.1109/icsai57119.2022.10005454" @default.
- W4313854518 hasPublicationYear "2022" @default.
- W4313854518 type Work @default.
- W4313854518 citedByCount "0" @default.
- W4313854518 crossrefType "proceedings-article" @default.
- W4313854518 hasAuthorship W4313854518A5003358015 @default.
- W4313854518 hasAuthorship W4313854518A5004708598 @default.
- W4313854518 hasAuthorship W4313854518A5014470931 @default.
- W4313854518 hasAuthorship W4313854518A5024519127 @default.
- W4313854518 hasAuthorship W4313854518A5031861539 @default.
- W4313854518 hasAuthorship W4313854518A5084984842 @default.
- W4313854518 hasConcept C111919701 @default.
- W4313854518 hasConcept C118505674 @default.
- W4313854518 hasConcept C118552586 @default.
- W4313854518 hasConcept C154945302 @default.
- W4313854518 hasConcept C15744967 @default.
- W4313854518 hasConcept C204321447 @default.
- W4313854518 hasConcept C206310091 @default.
- W4313854518 hasConcept C2777375102 @default.
- W4313854518 hasConcept C2777438025 @default.
- W4313854518 hasConcept C2779302386 @default.
- W4313854518 hasConcept C2779812673 @default.
- W4313854518 hasConcept C2780343955 @default.
- W4313854518 hasConcept C28490314 @default.
- W4313854518 hasConcept C41008148 @default.
- W4313854518 hasConcept C46312422 @default.
- W4313854518 hasConcept C95623464 @default.
- W4313854518 hasConceptScore W4313854518C111919701 @default.
- W4313854518 hasConceptScore W4313854518C118505674 @default.
- W4313854518 hasConceptScore W4313854518C118552586 @default.
- W4313854518 hasConceptScore W4313854518C154945302 @default.
- W4313854518 hasConceptScore W4313854518C15744967 @default.
- W4313854518 hasConceptScore W4313854518C204321447 @default.
- W4313854518 hasConceptScore W4313854518C206310091 @default.
- W4313854518 hasConceptScore W4313854518C2777375102 @default.
- W4313854518 hasConceptScore W4313854518C2777438025 @default.
- W4313854518 hasConceptScore W4313854518C2779302386 @default.
- W4313854518 hasConceptScore W4313854518C2779812673 @default.
- W4313854518 hasConceptScore W4313854518C2780343955 @default.
- W4313854518 hasConceptScore W4313854518C28490314 @default.
- W4313854518 hasConceptScore W4313854518C41008148 @default.
- W4313854518 hasConceptScore W4313854518C46312422 @default.
- W4313854518 hasConceptScore W4313854518C95623464 @default.
- W4313854518 hasLocation W43138545181 @default.
- W4313854518 hasOpenAccess W4313854518 @default.
- W4313854518 hasPrimaryLocation W43138545181 @default.
- W4313854518 hasRelatedWork W1988672169 @default.
- W4313854518 hasRelatedWork W2028755160 @default.
- W4313854518 hasRelatedWork W2078927943 @default.
- W4313854518 hasRelatedWork W2129256116 @default.
- W4313854518 hasRelatedWork W2177084713 @default.
- W4313854518 hasRelatedWork W2187276268 @default.
- W4313854518 hasRelatedWork W2328138258 @default.
- W4313854518 hasRelatedWork W2466104904 @default.
- W4313854518 hasRelatedWork W2588565917 @default.
- W4313854518 hasRelatedWork W3167551411 @default.
- W4313854518 isParatext "false" @default.
- W4313854518 isRetracted "false" @default.
- W4313854518 workType "article" @default.