no code implementations • XLI Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (SBrT2023) 2023 • Pedro H. L. Leite, Edmundo Hoyle, Álvaro Antelo, Luiz F. Kruszielski, Luiz W. P. Biscainho
This paper introduces a new dataset designed to address the limitations in high-quality, diverse and representative datasets for training text-to-speech (TTS) models, specifically for female voices in Brazilian Portuguese.
no code implementations • International Conference on Computational Processing of the Portuguese Language 2021 • Pedro H. L. Leite, Edmundo Hoyle, Álvaro Antelo, Luiz F. Kruszielski, Luiz W. P. Biscainho
This work presents a new database containing high sampling rate recordings of a single male speaker reading sentences in Brazilian Portuguese with neutral voice, along with the corresponding text corpus.