Matches in SemOpenAlex for { <https://semopenalex.org/work/W3122349645> ?p ?o ?g. }
- W3122349645 abstract "Pre-training for feature extraction is an increasingly studied approach to get better continuous representations of audio and text content. In the present work, we use wav2vec and camemBERT as self-supervised learned models to represent our data in order to perform continuous emotion recognition from speech (SER) on AlloSat, a large French emotional database describing the satisfaction dimension, and on the state of the art corpus SEWA focusing on valence, arousal and liking dimensions. To the authors' knowledge, this paper presents the first study showing that the joint use of wav2vec and BERT-like pre-trained features is very relevant to deal with continuous SER task, usually characterized by a small amount of labeled training data. Evaluated by the well-known concordance correlation coefficient (CCC), our experiments show that we can reach a CCC value of 0.825 instead of 0.592 when using MFCC in conjunction with word2vec word embedding on the AlloSat dataset." @default.
- W3122349645 created "2021-02-01" @default.
- W3122349645 creator A5028709353 @default.
- W3122349645 creator A5063176676 @default.
- W3122349645 creator A5081852717 @default.
- W3122349645 creator A5089715431 @default.
- W3122349645 date "2021-01-19" @default.
- W3122349645 modified "2023-10-16" @default.
- W3122349645 title "On the Use of Self-Supervised Pre-Trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition" @default.
- W3122349645 cites W1494198834 @default.
- W3122349645 cites W1876223856 @default.
- W3122349645 cites W2045528981 @default.
- W3122349645 cites W2085662862 @default.
- W3122349645 cites W2102998034 @default.
- W3122349645 cites W2239141610 @default.
- W3122349645 cites W2313339984 @default.
- W3122349645 cites W2621367454 @default.
- W3122349645 cites W2765815408 @default.
- W3122349645 cites W2798717312 @default.
- W3122349645 cites W2884001105 @default.
- W3122349645 cites W2897444637 @default.
- W3122349645 cites W2910165986 @default.
- W3122349645 cites W2953356739 @default.
- W3122349645 cites W2963854351 @default.
- W3122349645 cites W2972944488 @default.
- W3122349645 cites W2973049979 @default.
- W3122349645 cites W2981677410 @default.
- W3122349645 cites W2982223350 @default.
- W3122349645 cites W2986154550 @default.
- W3122349645 cites W2995181338 @default.
- W3122349645 cites W3049256661 @default.
- W3122349645 cites W3088876910 @default.
- W3122349645 cites W3101648800 @default.
- W3122349645 doi "https://doi.org/10.1109/slt48900.2021.9383456" @default.
- W3122349645 hasPublicationYear "2021" @default.
- W3122349645 type Work @default.
- W3122349645 sameAs 3122349645 @default.
- W3122349645 citedByCount "20" @default.
- W3122349645 countsByYear W31223496452021 @default.
- W3122349645 countsByYear W31223496452022 @default.
- W3122349645 countsByYear W31223496452023 @default.
- W3122349645 crossrefType "proceedings-article" @default.
- W3122349645 hasAuthorship W3122349645A5028709353 @default.
- W3122349645 hasAuthorship W3122349645A5063176676 @default.
- W3122349645 hasAuthorship W3122349645A5081852717 @default.
- W3122349645 hasAuthorship W3122349645A5089715431 @default.
- W3122349645 hasBestOaLocation W31223496452 @default.
- W3122349645 hasConcept C105795698 @default.
- W3122349645 hasConcept C121332964 @default.
- W3122349645 hasConcept C151989614 @default.
- W3122349645 hasConcept C154945302 @default.
- W3122349645 hasConcept C168900304 @default.
- W3122349645 hasConcept C202444582 @default.
- W3122349645 hasConcept C204321447 @default.
- W3122349645 hasConcept C2524010 @default.
- W3122349645 hasConcept C2776461190 @default.
- W3122349645 hasConcept C2777462759 @default.
- W3122349645 hasConcept C2781059462 @default.
- W3122349645 hasConcept C28490314 @default.
- W3122349645 hasConcept C33676613 @default.
- W3122349645 hasConcept C33923547 @default.
- W3122349645 hasConcept C41008148 @default.
- W3122349645 hasConcept C41608201 @default.
- W3122349645 hasConcept C52622490 @default.
- W3122349645 hasConcept C62520636 @default.
- W3122349645 hasConcept C90805587 @default.
- W3122349645 hasConceptScore W3122349645C105795698 @default.
- W3122349645 hasConceptScore W3122349645C121332964 @default.
- W3122349645 hasConceptScore W3122349645C151989614 @default.
- W3122349645 hasConceptScore W3122349645C154945302 @default.
- W3122349645 hasConceptScore W3122349645C168900304 @default.
- W3122349645 hasConceptScore W3122349645C202444582 @default.
- W3122349645 hasConceptScore W3122349645C204321447 @default.
- W3122349645 hasConceptScore W3122349645C2524010 @default.
- W3122349645 hasConceptScore W3122349645C2776461190 @default.
- W3122349645 hasConceptScore W3122349645C2777462759 @default.
- W3122349645 hasConceptScore W3122349645C2781059462 @default.
- W3122349645 hasConceptScore W3122349645C28490314 @default.
- W3122349645 hasConceptScore W3122349645C33676613 @default.
- W3122349645 hasConceptScore W3122349645C33923547 @default.
- W3122349645 hasConceptScore W3122349645C41008148 @default.
- W3122349645 hasConceptScore W3122349645C41608201 @default.
- W3122349645 hasConceptScore W3122349645C52622490 @default.
- W3122349645 hasConceptScore W3122349645C62520636 @default.
- W3122349645 hasConceptScore W3122349645C90805587 @default.
- W3122349645 hasLocation W31223496451 @default.
- W3122349645 hasLocation W31223496452 @default.
- W3122349645 hasLocation W31223496453 @default.
- W3122349645 hasLocation W31223496454 @default.
- W3122349645 hasOpenAccess W3122349645 @default.
- W3122349645 hasPrimaryLocation W31223496451 @default.
- W3122349645 hasRelatedWork W2747424680 @default.
- W3122349645 hasRelatedWork W2891550009 @default.
- W3122349645 hasRelatedWork W2952874106 @default.
- W3122349645 hasRelatedWork W2953749697 @default.
- W3122349645 hasRelatedWork W3036348210 @default.
- W3122349645 hasRelatedWork W3046869600 @default.
- W3122349645 hasRelatedWork W4246455502 @default.
- W3122349645 hasRelatedWork W4298857951 @default.
- W3122349645 hasRelatedWork W4313247739 @default.