Emotags: Computer-Assisted Verbal Labelling of Expressive Audiovisual Utterances for Expressive Multimodal TTS
Résumé
We developed a web app for ascribing verbal descriptions to expressive audiovisual utterances. These descriptions are limited to lists of adjective tags that are either suggested via a navigation in emotional latent spaces built using discriminant analysis of BERT embeddings, or entered freely by participants. We show that such verbal descriptions collected on-line via Prolific on massive French audiovisual data (742 participants, 8 970 tagged utterances up-to-now) provide Expressive MFciteultimodal Text-to-Speech Synthesis with precise verbal control over desired emotional content.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |