FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309708680> ?p ?o ?g. }

• W4309708680 endingPage "3831" @default.
• W4309708680 startingPage "3831" @default.
• W4309708680 abstract "Artificial Neural Network (ANN) models, specifically Convolutional Neural Networks (CNN), were applied to extract emotions based on spectrograms and mel-spectrograms. This study uses spectrograms and mel-spectrograms to investigate which feature extraction method better represents emotions and how big the differences in efficiency are in this context. The conducted studies demonstrated that mel-spectrograms are a better-suited data type for training CNN-based speech emotion recognition (SER). The research experiments employed five popular datasets: Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Surrey Audio-Visual Expressed Emotion (SAVEE), Toronto Emotional Speech Set (TESS), and The Interactive Emotional Dyadic Motion Capture (IEMOCAP). Six different classes of emotions were used: happiness, anger, sadness, fear, disgust, and neutral. However, some experiments were prepared to recognize just four emotions due to the characteristics of the IEMOCAP dataset. A comparison of classification efficiency on different datasets and an attempt to develop a universal model trained using all datasets were also performed. This approach brought an accuracy of 55.89% when recognizing four emotions. The most accurate model for six emotion recognition was trained and achieved 57.42% accuracy on a combination of four datasets (CREMA-D, RAVDESS, SAVEE, TESS). What is more, another study was developed that demonstrated that improper data division for training and test sets significantly influences the test accuracy of CNNs. Therefore, the problem of inappropriate data division between the training and test sets, which affected the results of studies known from the literature, was addressed extensively. The performed experiments employed the popular ResNet18 architecture to demonstrate the reliability of the research results and to show that these problems are not unique to the custom CNN architecture proposed in experiments. Subsequently, the label correctness of the CREMA-D dataset was studied through the employment of a prepared questionnaire." @default.
• W4309708680 created "2022-11-29" @default.
• W4309708680 creator A5015175702 @default.
• W4309708680 creator A5064591459 @default.
• W4309708680 creator A5065208915 @default.
• W4309708680 creator A5079397804 @default.
• W4309708680 creator A5084917603 @default.
• W4309708680 creator A5085913590 @default.
• W4309708680 date "2022-11-21" @default.
• W4309708680 modified "2023-10-01" @default.
• W4309708680 title "Recognition of Emotions in Speech Using Convolutional Neural Networks on Different Datasets" @default.
• W4309708680 cites W1832693441 @default.
• W4309708680 cites W2030931454 @default.
• W4309708680 cites W2074788634 @default.
• W4309708680 cites W2120615054 @default.
• W4309708680 cites W2146334809 @default.
• W4309708680 cites W2181741066 @default.
• W4309708680 cites W2194775991 @default.
• W4309708680 cites W2399733683 @default.
• W4309708680 cites W2598207902 @default.
• W4309708680 cites W2750666523 @default.
• W4309708680 cites W2786121637 @default.
• W4309708680 cites W2803193013 @default.
• W4309708680 cites W2889717020 @default.
• W4309708680 cites W2901120086 @default.
• W4309708680 cites W2936451900 @default.
• W4309708680 cites W2951442257 @default.
• W4309708680 cites W2969889150 @default.
• W4309708680 cites W2970737019 @default.
• W4309708680 cites W2996607328 @default.
• W4309708680 cites W3006926732 @default.
• W4309708680 cites W3008130537 @default.
• W4309708680 cites W3008554267 @default.
• W4309708680 cites W3015267357 @default.
• W4309708680 cites W3094273504 @default.
• W4309708680 cites W3095612572 @default.
• W4309708680 cites W3096136448 @default.
• W4309708680 cites W3116444723 @default.
• W4309708680 cites W3161428216 @default.
• W4309708680 cites W3175772607 @default.
• W4309708680 cites W3198908807 @default.
• W4309708680 cites W3207346153 @default.
• W4309708680 cites W3209072429 @default.
• W4309708680 cites W4210930550 @default.
• W4309708680 cites W4221072225 @default.
• W4309708680 cites W4225959162 @default.
• W4309708680 cites W4228996454 @default.
• W4309708680 doi "https://doi.org/10.3390/electronics11223831" @default.
• W4309708680 hasPublicationYear "2022" @default.
• W4309708680 type Work @default.
• W4309708680 citedByCount "2" @default.
• W4309708680 countsByYear W43097086802022 @default.
• W4309708680 countsByYear W43097086802023 @default.
• W4309708680 crossrefType "journal-article" @default.
• W4309708680 hasAuthorship W4309708680A5015175702 @default.
• W4309708680 hasAuthorship W4309708680A5064591459 @default.
• W4309708680 hasAuthorship W4309708680A5065208915 @default.
• W4309708680 hasAuthorship W4309708680A5079397804 @default.
• W4309708680 hasAuthorship W4309708680A5084917603 @default.
• W4309708680 hasAuthorship W4309708680A5085913590 @default.
• W4309708680 hasBestOaLocation W43097086801 @default.
• W4309708680 hasConcept C118552586 @default.
• W4309708680 hasConcept C138885662 @default.
• W4309708680 hasConcept C151730666 @default.
• W4309708680 hasConcept C154945302 @default.
• W4309708680 hasConcept C15744967 @default.
• W4309708680 hasConcept C169903167 @default.
• W4309708680 hasConcept C177264268 @default.
• W4309708680 hasConcept C199360897 @default.
• W4309708680 hasConcept C206310091 @default.
• W4309708680 hasConcept C2776401178 @default.
• W4309708680 hasConcept C2777375102 @default.
• W4309708680 hasConcept C2779302386 @default.
• W4309708680 hasConcept C2779343474 @default.
• W4309708680 hasConcept C2779812673 @default.
• W4309708680 hasConcept C28490314 @default.
• W4309708680 hasConcept C41008148 @default.
• W4309708680 hasConcept C41895202 @default.
• W4309708680 hasConcept C45273575 @default.
• W4309708680 hasConcept C81363708 @default.
• W4309708680 hasConcept C86803240 @default.
• W4309708680 hasConceptScore W4309708680C118552586 @default.
• W4309708680 hasConceptScore W4309708680C138885662 @default.
• W4309708680 hasConceptScore W4309708680C151730666 @default.
• W4309708680 hasConceptScore W4309708680C154945302 @default.
• W4309708680 hasConceptScore W4309708680C15744967 @default.
• W4309708680 hasConceptScore W4309708680C169903167 @default.
• W4309708680 hasConceptScore W4309708680C177264268 @default.
• W4309708680 hasConceptScore W4309708680C199360897 @default.
• W4309708680 hasConceptScore W4309708680C206310091 @default.
• W4309708680 hasConceptScore W4309708680C2776401178 @default.
• W4309708680 hasConceptScore W4309708680C2777375102 @default.
• W4309708680 hasConceptScore W4309708680C2779302386 @default.
• W4309708680 hasConceptScore W4309708680C2779343474 @default.
• W4309708680 hasConceptScore W4309708680C2779812673 @default.
• W4309708680 hasConceptScore W4309708680C28490314 @default.
• W4309708680 hasConceptScore W4309708680C41008148 @default.
• W4309708680 hasConceptScore W4309708680C41895202 @default.

• next