Emotags: Computer-Assisted Verbal Labelling of Expressive Audiovisual Utterances for Expressive Multimodal TTS
Gérard Bailly, Romain Legrand, Martin Lenglet, Frédéric Elisei, Maëva Hueber, Olivier Perrotin
Abstract
We developped a web app for ascribing verbal descriptions to expressive audiovisual utterances. These descriptions are limited to lists of adjectives that are either suggested via a navigation in emotional latent spaces built using discriminant analysis of BERT embeddings or entered freely by subjects. We show that such verbal descriptions collected on-line via Prolific on massive data (310 participants, 12620 labelled utterances up-to-now) provide Expressive Multimodal Text-to-Speech Synthesis with precise verbal control over desired emotional content- Anthology ID:
- 2024.lrec-main.505
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 5689–5695
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.505
- DOI:
- Cite (ACL):
- Gérard Bailly, Romain Legrand, Martin Lenglet, Frédéric Elisei, Maëva Hueber, and Olivier Perrotin. 2024. Emotags: Computer-Assisted Verbal Labelling of Expressive Audiovisual Utterances for Expressive Multimodal TTS. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5689–5695, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- Emotags: Computer-Assisted Verbal Labelling of Expressive Audiovisual Utterances for Expressive Multimodal TTS (Bailly et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2024.lrec-main.505.pdf