FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2766272105> ?p ?o ?g. }

• W2766272105 endingPage "1590" @default.
• W2766272105 startingPage "1576" @default.
• W2766272105 abstract "Speech emotion recognition is challenging because of the affective gap between the subjective emotions and low-level features. Integrating multilevel feature learning and model training, deep convolutional neural networks (DCNN) has exhibited remarkable success in bridging the semantic gap in visual tasks like image classification, object detection. This paper explores how to utilize a DCNN to bridge the affective gap in speech signals. To this end, we first extract three channels of log Mel-spectrograms (static, delta, and delta delta) similar to the red, green, blue (RGB) image representation as the DCNN input. Then, the AlexNet DCNN model pretrained on the large ImageNet dataset is employed to learn high-level feature representations on each segment divided from an utterance. The learned segment-level features are aggregated by a discriminant temporal pyramid matching (DTPM) strategy. DTPM combines temporal pyramid matching and optimal Lp-norm pooling to form a global utterance-level feature representation, followed by the linear support vector machines for emotion classification. Experimental results on four public datasets, that is, EMO-DB, RML, eNTERFACE05, and BAUM-1s, show the promising performance of our DCNN model and the DTPM strategy. Another interesting finding is that the DCNN model pretrained for image applications performs reasonably good in affective speech feature extraction. Further fine tuning on the target emotional speech datasets substantially promotes recognition performance." @default.
• W2766272105 created "2017-11-10" @default.
• W2766272105 creator A5018478553 @default.
• W2766272105 creator A5058066577 @default.
• W2766272105 creator A5086152036 @default.
• W2766272105 date "2018-06-01" @default.
• W2766272105 modified "2023-10-14" @default.
• W2766272105 title "Speech Emotion Recognition Using Deep Convolutional Neural Network and Discriminant Temporal Pyramid Matching" @default.
• W2766272105 cites W1483399002 @default.
• W2766272105 cites W1534131679 @default.
• W2766272105 cites W1923034539 @default.
• W2766272105 cites W1934410531 @default.
• W2766272105 cites W1963882359 @default.
• W2766272105 cites W1980299015 @default.
• W2766272105 cites W1995562189 @default.
• W2766272105 cites W2001619934 @default.
• W2766272105 cites W2023937851 @default.
• W2766272105 cites W2026243162 @default.
• W2766272105 cites W2030670342 @default.
• W2766272105 cites W2030739378 @default.
• W2766272105 cites W2032254851 @default.
• W2766272105 cites W2045528981 @default.
• W2766272105 cites W2046554340 @default.
• W2766272105 cites W2055911634 @default.
• W2766272105 cites W2064641533 @default.
• W2766272105 cites W2064675550 @default.
• W2766272105 cites W2074788634 @default.
• W2766272105 cites W2080289724 @default.
• W2766272105 cites W2080576537 @default.
• W2766272105 cites W2083543775 @default.
• W2766272105 cites W2087195460 @default.
• W2766272105 cites W2087618018 @default.
• W2766272105 cites W2092718714 @default.
• W2766272105 cites W2097117768 @default.
• W2766272105 cites W2098507061 @default.
• W2766272105 cites W2099767163 @default.
• W2766272105 cites W2100495367 @default.
• W2766272105 cites W2104773730 @default.
• W2766272105 cites W2111926505 @default.
• W2766272105 cites W2112796928 @default.
• W2766272105 cites W2117951582 @default.
• W2766272105 cites W2118911453 @default.
• W2766272105 cites W2119534679 @default.
• W2766272105 cites W2132555391 @default.
• W2766272105 cites W2140801466 @default.
• W2766272105 cites W2144264893 @default.
• W2766272105 cites W2146879304 @default.
• W2766272105 cites W2147634797 @default.
• W2766272105 cites W2153635508 @default.
• W2766272105 cites W2158061940 @default.
• W2766272105 cites W2158874389 @default.
• W2766272105 cites W2160815625 @default.
• W2766272105 cites W2161073241 @default.
• W2766272105 cites W2161372178 @default.
• W2766272105 cites W2162915993 @default.
• W2766272105 cites W2168045655 @default.
• W2766272105 cites W2239141610 @default.
• W2766272105 cites W2260176752 @default.
• W2766272105 cites W2336160298 @default.
• W2766272105 cites W2394859829 @default.
• W2766272105 cites W2399733683 @default.
• W2766272105 cites W2508202655 @default.
• W2766272105 cites W2618530766 @default.
• W2766272105 cites W3141819983 @default.
• W2766272105 cites W3148981562 @default.
• W2766272105 doi "https://doi.org/10.1109/tmm.2017.2766843" @default.
• W2766272105 hasPublicationYear "2018" @default.
• W2766272105 type Work @default.
• W2766272105 sameAs 2766272105 @default.
• W2766272105 citedByCount "272" @default.
• W2766272105 countsByYear W27662721052018 @default.
• W2766272105 countsByYear W27662721052019 @default.
• W2766272105 countsByYear W27662721052020 @default.
• W2766272105 countsByYear W27662721052021 @default.
• W2766272105 countsByYear W27662721052022 @default.
• W2766272105 countsByYear W27662721052023 @default.
• W2766272105 crossrefType "journal-article" @default.
• W2766272105 hasAuthorship W2766272105A5018478553 @default.
• W2766272105 hasAuthorship W2766272105A5058066577 @default.
• W2766272105 hasAuthorship W2766272105A5086152036 @default.
• W2766272105 hasConcept C138885662 @default.
• W2766272105 hasConcept C142575187 @default.
• W2766272105 hasConcept C153180895 @default.
• W2766272105 hasConcept C154945302 @default.
• W2766272105 hasConcept C2524010 @default.
• W2766272105 hasConcept C2776401178 @default.
• W2766272105 hasConcept C28490314 @default.
• W2766272105 hasConcept C33923547 @default.
• W2766272105 hasConcept C41008148 @default.
• W2766272105 hasConcept C41895202 @default.
• W2766272105 hasConcept C52622490 @default.
• W2766272105 hasConcept C59404180 @default.
• W2766272105 hasConcept C69738355 @default.
• W2766272105 hasConcept C70437156 @default.
• W2766272105 hasConcept C81363708 @default.
• W2766272105 hasConceptScore W2766272105C138885662 @default.
• W2766272105 hasConceptScore W2766272105C142575187 @default.
• W2766272105 hasConceptScore W2766272105C153180895 @default.

• next