Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893513420> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2893513420 abstract "Speech emotion recognition (SER) is a challenging task with many problems unsolved, such as extracting representative features and dealing with imbalanced training data. For the past few decades, much research has been done in this area, but the performance is still far from satisfying. In this paper, we propose an Ensemble System which fuses four different subsystems. TDNN (Time Delay Neural Network) System uses a neural network with p-norm and time delay as the classifier. i-vector/SVM (Support Vector Machine) System learns the acoustic feature from i-vector space. Simple Late Fusion System fuses different features on the decision level while Balanced Late Fusion System introduces a data rebalance module to rebalance the class distribution of the training samples. The overall Ensemble System takes the advantages of each subsystem on the decision level. Experiments are conducted on the CHEAVD 2.0 database which is provided in the Multimodal Emotion Recognition Challenge. The results of the Simple Late Fusion System on the test set outperforms the baseline system by 3.9% and 6.9% on Accuracy (ACC) and Macro Average Precision (MAP), respectively. Our results indicate that the Simple Late Fusion System is more effective on ACC and MAP while the Balanced Late Fusion System outperforms other systems on Macro Average Recall and Macro Average F1." @default.
- W2893513420 created "2018-10-05" @default.
- W2893513420 creator A5005083870 @default.
- W2893513420 creator A5053533157 @default.
- W2893513420 creator A5084318285 @default.
- W2893513420 date "2018-05-01" @default.
- W2893513420 modified "2023-09-22" @default.
- W2893513420 title "Ensemble System for Multimodal Emotion Recognition Challenge (MEC 2017)" @default.
- W2893513420 cites W1501669607 @default.
- W2893513420 cites W1524333225 @default.
- W2893513420 cites W1576079953 @default.
- W2893513420 cites W1972280480 @default.
- W2893513420 cites W1994458317 @default.
- W2893513420 cites W2037441721 @default.
- W2893513420 cites W2074788634 @default.
- W2893513420 cites W2085662862 @default.
- W2893513420 cites W2111926505 @default.
- W2893513420 cites W2118911453 @default.
- W2893513420 cites W2119821739 @default.
- W2893513420 cites W2167917621 @default.
- W2893513420 cites W2296199791 @default.
- W2893513420 cites W2395587375 @default.
- W2893513420 cites W2402146185 @default.
- W2893513420 cites W2477594834 @default.
- W2893513420 cites W2579011716 @default.
- W2893513420 cites W2610961739 @default.
- W2893513420 cites W2637507649 @default.
- W2893513420 cites W2707551695 @default.
- W2893513420 cites W2750666523 @default.
- W2893513420 cites W2757184610 @default.
- W2893513420 cites W2775696145 @default.
- W2893513420 cites W2894458059 @default.
- W2893513420 cites W2911964244 @default.
- W2893513420 doi "https://doi.org/10.1109/aciiasia.2018.8470352" @default.
- W2893513420 hasPublicationYear "2018" @default.
- W2893513420 type Work @default.
- W2893513420 sameAs 2893513420 @default.
- W2893513420 citedByCount "1" @default.
- W2893513420 countsByYear W28935134202021 @default.
- W2893513420 crossrefType "proceedings-article" @default.
- W2893513420 hasAuthorship W2893513420A5005083870 @default.
- W2893513420 hasAuthorship W2893513420A5053533157 @default.
- W2893513420 hasAuthorship W2893513420A5084318285 @default.
- W2893513420 hasConcept C119857082 @default.
- W2893513420 hasConcept C12267149 @default.
- W2893513420 hasConcept C153180895 @default.
- W2893513420 hasConcept C154945302 @default.
- W2893513420 hasConcept C166955791 @default.
- W2893513420 hasConcept C199360897 @default.
- W2893513420 hasConcept C28490314 @default.
- W2893513420 hasConcept C33954974 @default.
- W2893513420 hasConcept C41008148 @default.
- W2893513420 hasConcept C50644808 @default.
- W2893513420 hasConcept C83665646 @default.
- W2893513420 hasConcept C95623464 @default.
- W2893513420 hasConceptScore W2893513420C119857082 @default.
- W2893513420 hasConceptScore W2893513420C12267149 @default.
- W2893513420 hasConceptScore W2893513420C153180895 @default.
- W2893513420 hasConceptScore W2893513420C154945302 @default.
- W2893513420 hasConceptScore W2893513420C166955791 @default.
- W2893513420 hasConceptScore W2893513420C199360897 @default.
- W2893513420 hasConceptScore W2893513420C28490314 @default.
- W2893513420 hasConceptScore W2893513420C33954974 @default.
- W2893513420 hasConceptScore W2893513420C41008148 @default.
- W2893513420 hasConceptScore W2893513420C50644808 @default.
- W2893513420 hasConceptScore W2893513420C83665646 @default.
- W2893513420 hasConceptScore W2893513420C95623464 @default.
- W2893513420 hasLocation W28935134201 @default.
- W2893513420 hasOpenAccess W2893513420 @default.
- W2893513420 hasPrimaryLocation W28935134201 @default.
- W2893513420 hasRelatedWork W1996423054 @default.
- W2893513420 hasRelatedWork W2295001676 @default.
- W2893513420 hasRelatedWork W2408520939 @default.
- W2893513420 hasRelatedWork W2548899748 @default.
- W2893513420 hasRelatedWork W2624578427 @default.
- W2893513420 hasRelatedWork W2787584921 @default.
- W2893513420 hasRelatedWork W2796509113 @default.
- W2893513420 hasRelatedWork W2895358653 @default.
- W2893513420 hasRelatedWork W2897428527 @default.
- W2893513420 hasRelatedWork W2898697562 @default.
- W2893513420 hasRelatedWork W2924126491 @default.
- W2893513420 hasRelatedWork W2945956523 @default.
- W2893513420 hasRelatedWork W2964747519 @default.
- W2893513420 hasRelatedWork W3045352664 @default.
- W2893513420 hasRelatedWork W3095648847 @default.
- W2893513420 hasRelatedWork W3101629877 @default.
- W2893513420 hasRelatedWork W3131976674 @default.
- W2893513420 hasRelatedWork W3154935508 @default.
- W2893513420 hasRelatedWork W3179560930 @default.
- W2893513420 hasRelatedWork W3204087964 @default.
- W2893513420 isParatext "false" @default.
- W2893513420 isRetracted "false" @default.
- W2893513420 magId "2893513420" @default.
- W2893513420 workType "article" @default.