Papers by Daniel Tunnermann
BRSpeech-DF: A Deep Fake Synthetic Speech Dataset for Portuguese Zero-Shot TTS (2025.emnlp-main)
Copied to clipboard
Alexandre Costa Ferro Filho, Rafaello Virgilli, Lucas Alcantara Souza, F S de Oliveira, Marcelo Henrique Lopes Ferreira, Daniel Tunnermann, Gustavo Dos Reis Oliveira, Anderson Da Silva Soares, Arlindo Rodrigues Galvão Filho
| Challenge: | ADD detection is a key area of research for low-resource languages like Portuguese, which lacks high-quality datasets. |
| Approach: | They propose to provide the first publicly available ADD dataset for Portuguese, encompassing both Brazilian and European variants. |
| Outcome: | The proposed dataset contains over 458,000 utterances, including a smaller portion of real speech from 62 speakers and a large collection of synthetic samples generated using multiple zero-shot text-to-speech (TTS) models, each conditioned on the original speaker’s voice. |