Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000256674> ?p ?o ?g. }
- W3000256674 abstract "Self supervised representation learning has recently attracted a lot of research interest for both the audio and visual modalities. However, most works typically focus on a particular modality or feature alone and there has been very limited work that studies the interaction between the two modalities for learning self supervised representations. We propose a framework for learning audio representations guided by the visual modality in the context of audiovisual speech. We employ a generative audio-to-video training scheme in which we animate a still image corresponding to a given audio clip and optimize the generated video to be as close as possible to the real video of the speech segment. Through this process, the audio encoder network learns useful speech representations that we evaluate on emotion recognition and speech recognition. We achieve state of the art results for emotion recognition and competitive results for speech recognition. This demonstrates the potential of visual supervision for learning audio representations as a novel way for self-supervised learning which has not been explored in the past. The proposed unsupervised audio features can leverage a virtually unlimited amount of training data of unlabelled audiovisual speech and have a large number of potentially promising applications." @default.
- W3000256674 created "2020-01-23" @default.
- W3000256674 creator A5001790767 @default.
- W3000256674 creator A5008824409 @default.
- W3000256674 creator A5009475700 @default.
- W3000256674 creator A5016033078 @default.
- W3000256674 creator A5079503255 @default.
- W3000256674 date "2020-01-13" @default.
- W3000256674 modified "2023-09-27" @default.
- W3000256674 title "Visually Guided Self Supervised Learning of Speech Representations" @default.
- W3000256674 cites W1901129140 @default.
- W3000256674 cites W2015143272 @default.
- W3000256674 cites W2029199293 @default.
- W3000256674 cites W2030931454 @default.
- W3000256674 cites W2261706002 @default.
- W3000256674 cites W2594690981 @default.
- W3000256674 cites W2787560479 @default.
- W3000256674 cites W2796992393 @default.
- W3000256674 cites W2797583228 @default.
- W3000256674 cites W2803193013 @default.
- W3000256674 cites W2804600264 @default.
- W3000256674 cites W2842511635 @default.
- W3000256674 cites W2902368158 @default.
- W3000256674 cites W2926827382 @default.
- W3000256674 cites W2935542736 @default.
- W3000256674 cites W2962742544 @default.
- W3000256674 cites W2962780374 @default.
- W3000256674 cites W2962931510 @default.
- W3000256674 cites W2962969419 @default.
- W3000256674 cites W2963115079 @default.
- W3000256674 cites W2963341956 @default.
- W3000256674 cites W2964048159 @default.
- W3000256674 cites W2973049979 @default.
- W3000256674 cites W343636949 @default.
- W3000256674 cites W2947454875 @default.
- W3000256674 hasPublicationYear "2020" @default.
- W3000256674 type Work @default.
- W3000256674 sameAs 3000256674 @default.
- W3000256674 citedByCount "0" @default.
- W3000256674 crossrefType "posted-content" @default.
- W3000256674 hasAuthorship W3000256674A5001790767 @default.
- W3000256674 hasAuthorship W3000256674A5008824409 @default.
- W3000256674 hasAuthorship W3000256674A5009475700 @default.
- W3000256674 hasAuthorship W3000256674A5016033078 @default.
- W3000256674 hasAuthorship W3000256674A5079503255 @default.
- W3000256674 hasConcept C111919701 @default.
- W3000256674 hasConcept C118505674 @default.
- W3000256674 hasConcept C120665830 @default.
- W3000256674 hasConcept C121332964 @default.
- W3000256674 hasConcept C138885662 @default.
- W3000256674 hasConcept C144024400 @default.
- W3000256674 hasConcept C151730666 @default.
- W3000256674 hasConcept C153083717 @default.
- W3000256674 hasConcept C154945302 @default.
- W3000256674 hasConcept C192209626 @default.
- W3000256674 hasConcept C2776401178 @default.
- W3000256674 hasConcept C2779343474 @default.
- W3000256674 hasConcept C2779903281 @default.
- W3000256674 hasConcept C2780226545 @default.
- W3000256674 hasConcept C28490314 @default.
- W3000256674 hasConcept C3017588708 @default.
- W3000256674 hasConcept C36289849 @default.
- W3000256674 hasConcept C41008148 @default.
- W3000256674 hasConcept C41895202 @default.
- W3000256674 hasConcept C49774154 @default.
- W3000256674 hasConcept C59404180 @default.
- W3000256674 hasConcept C86803240 @default.
- W3000256674 hasConcept C98045186 @default.
- W3000256674 hasConceptScore W3000256674C111919701 @default.
- W3000256674 hasConceptScore W3000256674C118505674 @default.
- W3000256674 hasConceptScore W3000256674C120665830 @default.
- W3000256674 hasConceptScore W3000256674C121332964 @default.
- W3000256674 hasConceptScore W3000256674C138885662 @default.
- W3000256674 hasConceptScore W3000256674C144024400 @default.
- W3000256674 hasConceptScore W3000256674C151730666 @default.
- W3000256674 hasConceptScore W3000256674C153083717 @default.
- W3000256674 hasConceptScore W3000256674C154945302 @default.
- W3000256674 hasConceptScore W3000256674C192209626 @default.
- W3000256674 hasConceptScore W3000256674C2776401178 @default.
- W3000256674 hasConceptScore W3000256674C2779343474 @default.
- W3000256674 hasConceptScore W3000256674C2779903281 @default.
- W3000256674 hasConceptScore W3000256674C2780226545 @default.
- W3000256674 hasConceptScore W3000256674C28490314 @default.
- W3000256674 hasConceptScore W3000256674C3017588708 @default.
- W3000256674 hasConceptScore W3000256674C36289849 @default.
- W3000256674 hasConceptScore W3000256674C41008148 @default.
- W3000256674 hasConceptScore W3000256674C41895202 @default.
- W3000256674 hasConceptScore W3000256674C49774154 @default.
- W3000256674 hasConceptScore W3000256674C59404180 @default.
- W3000256674 hasConceptScore W3000256674C86803240 @default.
- W3000256674 hasConceptScore W3000256674C98045186 @default.
- W3000256674 hasLocation W30002566741 @default.
- W3000256674 hasOpenAccess W3000256674 @default.
- W3000256674 hasPrimaryLocation W30002566741 @default.
- W3000256674 hasRelatedWork W2608612081 @default.
- W3000256674 hasRelatedWork W2740883964 @default.
- W3000256674 hasRelatedWork W2809767522 @default.
- W3000256674 hasRelatedWork W2972463723 @default.
- W3000256674 hasRelatedWork W3015356123 @default.
- W3000256674 hasRelatedWork W3017923487 @default.