Matches in SemOpenAlex for { <https://semopenalex.org/work/W3025642987> ?p ?o ?g. }
- W3025642987 abstract "Research in advancing speech emotion recognition (SER) has attracted a lot of attention due to its critical role for better human behaviors understanding scientifically and comprehensive applications commercially. Conventionally, performing SER highly relies on hand-crafted acoustic features. The recent progress in deep learning has attempted to model emotion directly from raw waveform in an end-to-end learning scheme; however, this particular approach remains to be generally a sub-optimal approach. An alternative direction has been proposed to enhance and augment the knowledge-based acoustic representation with affect-related representation derived directly from raw waveform. Here, we propose a complimentary waveform-feature dual branch learning network, termed as Dual-Complementary Acoustic Embedding Network (DCaEN), to effectively integrate psychoacoustic knowledge and raw waveform embedding within an augmented feature space learning approach. DCaEN contains an acoustic feature embedding network and a raw waveform network, that is learned by integrating negative cosine distance constraint in the loss function. The experiment results show that DCaEN can achieve 59.31% an 46.73% unweighted average recall (UAR) in the USC IEMOCAP and the MSP-IMPROV speech emotion databases, which improves the performance compared to modeling either acoustic hand-crafted features or raw waveform only and without this particular loss constraint. Further analysis illustrates a reverse mirroring pattern in the learned latent space demonstrating the complementary nature of DCaEN feature space learning." @default.
- W3025642987 created "2020-05-21" @default.
- W3025642987 creator A5001894880 @default.
- W3025642987 creator A5022951629 @default.
- W3025642987 creator A5062975307 @default.
- W3025642987 creator A5086107623 @default.
- W3025642987 date "2020-05-15" @default.
- W3025642987 modified "2023-10-18" @default.
- W3025642987 title "A Waveform-Feature Dual Branch Acoustic Embedding Network for Emotion Recognition" @default.
- W3025642987 cites W147964346 @default.
- W3025642987 cites W1844030040 @default.
- W3025642987 cites W1972280480 @default.
- W3025642987 cites W2016661008 @default.
- W3025642987 cites W2037441721 @default.
- W3025642987 cites W2055911634 @default.
- W3025642987 cites W2060198345 @default.
- W3025642987 cites W2074187690 @default.
- W3025642987 cites W2074788634 @default.
- W3025642987 cites W2077644276 @default.
- W3025642987 cites W2090777335 @default.
- W3025642987 cites W2111926505 @default.
- W3025642987 cites W2114256784 @default.
- W3025642987 cites W2119417805 @default.
- W3025642987 cites W2121139690 @default.
- W3025642987 cites W2141853407 @default.
- W3025642987 cites W2144005487 @default.
- W3025642987 cites W2146334809 @default.
- W3025642987 cites W2159408788 @default.
- W3025642987 cites W2239141610 @default.
- W3025642987 cites W2295001676 @default.
- W3025642987 cites W2298261874 @default.
- W3025642987 cites W2342475039 @default.
- W3025642987 cites W2408520939 @default.
- W3025642987 cites W2598207902 @default.
- W3025642987 cites W2602034649 @default.
- W3025642987 cites W2625297138 @default.
- W3025642987 cites W2766756589 @default.
- W3025642987 cites W2889107526 @default.
- W3025642987 cites W2889191349 @default.
- W3025642987 cites W2889191742 @default.
- W3025642987 cites W2889462515 @default.
- W3025642987 cites W2889717020 @default.
- W3025642987 cites W2892071465 @default.
- W3025642987 cites W2892921685 @default.
- W3025642987 cites W2917572534 @default.
- W3025642987 cites W2951123823 @default.
- W3025642987 cites W2951975883 @default.
- W3025642987 cites W2962736520 @default.
- W3025642987 cites W2962993399 @default.
- W3025642987 cites W2973037561 @default.
- W3025642987 cites W2995506319 @default.
- W3025642987 doi "https://doi.org/10.3389/fcomp.2020.00013" @default.
- W3025642987 hasPublicationYear "2020" @default.
- W3025642987 type Work @default.
- W3025642987 sameAs 3025642987 @default.
- W3025642987 citedByCount "2" @default.
- W3025642987 countsByYear W30256429872021 @default.
- W3025642987 countsByYear W30256429872023 @default.
- W3025642987 crossrefType "journal-article" @default.
- W3025642987 hasAuthorship W3025642987A5001894880 @default.
- W3025642987 hasAuthorship W3025642987A5022951629 @default.
- W3025642987 hasAuthorship W3025642987A5062975307 @default.
- W3025642987 hasAuthorship W3025642987A5086107623 @default.
- W3025642987 hasBestOaLocation W30256429871 @default.
- W3025642987 hasConcept C138885662 @default.
- W3025642987 hasConcept C153180895 @default.
- W3025642987 hasConcept C154945302 @default.
- W3025642987 hasConcept C17744445 @default.
- W3025642987 hasConcept C197424946 @default.
- W3025642987 hasConcept C199539241 @default.
- W3025642987 hasConcept C2524010 @default.
- W3025642987 hasConcept C2776036281 @default.
- W3025642987 hasConcept C2776359362 @default.
- W3025642987 hasConcept C2776401178 @default.
- W3025642987 hasConcept C28490314 @default.
- W3025642987 hasConcept C33923547 @default.
- W3025642987 hasConcept C41008148 @default.
- W3025642987 hasConcept C41608201 @default.
- W3025642987 hasConcept C41895202 @default.
- W3025642987 hasConcept C554190296 @default.
- W3025642987 hasConcept C59404180 @default.
- W3025642987 hasConcept C76155785 @default.
- W3025642987 hasConcept C83665646 @default.
- W3025642987 hasConcept C94625758 @default.
- W3025642987 hasConceptScore W3025642987C138885662 @default.
- W3025642987 hasConceptScore W3025642987C153180895 @default.
- W3025642987 hasConceptScore W3025642987C154945302 @default.
- W3025642987 hasConceptScore W3025642987C17744445 @default.
- W3025642987 hasConceptScore W3025642987C197424946 @default.
- W3025642987 hasConceptScore W3025642987C199539241 @default.
- W3025642987 hasConceptScore W3025642987C2524010 @default.
- W3025642987 hasConceptScore W3025642987C2776036281 @default.
- W3025642987 hasConceptScore W3025642987C2776359362 @default.
- W3025642987 hasConceptScore W3025642987C2776401178 @default.
- W3025642987 hasConceptScore W3025642987C28490314 @default.
- W3025642987 hasConceptScore W3025642987C33923547 @default.
- W3025642987 hasConceptScore W3025642987C41008148 @default.
- W3025642987 hasConceptScore W3025642987C41608201 @default.
- W3025642987 hasConceptScore W3025642987C41895202 @default.
- W3025642987 hasConceptScore W3025642987C554190296 @default.