Maia Ranniery
Maia Ranniery has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Daniel G. de P. Zanco
Análise Comparativa das Arquiteturas de Rajpurkar et al
1 shared publication - Eduardo Vinicius Kuhn
Federal University of Technology -Paraná 85902-490 Toledo Paraná Brazil
1 shared publication - Luiz Wagner Pereira Biscainho
DEL/Poli, Universidade Federal do Rio de Janeiro; PEE/COPPE, Universidade Federal do Rio de Janeiro
1 shared publication Sarah Morgana Meurer
Análise Comparativa das Arquiteturas de Rajpurkar et al
1 shared publication- Sergio L. Netto
UFRJ
1 shared publication Universidade Federal do Rio Grande do Norte
1 shared publication
Latest Publications
- Open Access
- 1 January 2024
- Published by Sociedad Brasileira de Telecomunicacoes in Journal of Communication and Information Systems
- Vol. 39 (1) , 127-136
A Pitch-Controlled End-to-End Voice Conversion System for Brazilian Portuguese
Speech conversion is a technique that modifies the identity of the voice in a speech signal without changing the spoken content. Accurate pitch conversion is a requirement the best speech conversion systems must address, as this characteristic is essential to the correct identification of the target speaker. This work proposes a pitch-controlled end-to-end voice conversion model that combines state-of-the-art ideas from both speaking and singing voice conversion with a novel cost function to ensure artifact-free pitch tracking. The model is trained in Brazilian Portuguese, overcoming the lack of high-quality data by improving a large but flawed dataset with filtering operation. Our model mostly outperforms other popular open source models in both listening tests and objective measurements. In particular, on a 5-point MOS, we obtained the highest speaker similarity score (4.05), and a naturalness score of 3.48, second only to a system whose similarity score was 2.62.
- 1 January 2024
- Published by Sociedad Brasileira de Telecomunicacoes in Journal of Communication and Information Systems
- Vol. 39 (1) , 127-136
Open AccessA Pitch-Controlled End-to-End Voice Conversion System for Brazilian Portuguese
Speech conversion is a technique that modifies the identity of the voice in a speech signal without changing the spoken content. Accurate pitch conversion is a requirement the best speech conversion systems must address, as this characteristic is essential to the correct identification of the target speaker. This work proposes a pitch-controlled end-to-end voice conversion model that combines state-of-the-art ideas from both speaking and singing voice conversion with a novel cost function to ensure artifact-free pitch tracking. The model is trained in Brazilian Portuguese, overcoming the lack of high-quality data by improving a large but flawed dataset with filtering operation. Our model mostly outperforms other popular open source models in both listening tests and objective measurements. In particular, on a 5-point MOS, we obtained the highest speaker similarity score (4.05), and a naturalness score of 3.48, second only to a system whose similarity score was 2.62.
- Open Access
- 1 January 2023
- Published by Sociedad Brasileira de Telecomunicacoes
Análise Comparativa das Arquiteturas de Rajpurkar et al. e Ribeiro et al. para Classificação de Patologias Cardíacas em Eletrocardiogramas
Resumo-Este trabalho foca na avaliação de desempenho de duas arquiteturas relevantes introduzidas para detecção e classificação de patologias cardíacas. Tais arquiteturas
- 1 January 2023
- Published by Sociedad Brasileira de Telecomunicacoes
Open AccessAnálise Comparativa das Arquiteturas de Rajpurkar et al. e Ribeiro et al. para Classificação de Patologias Cardíacas em Eletrocardiogramas
Resumo-Este trabalho foca na avaliação de desempenho de duas arquiteturas relevantes introduzidas para detecção e classificação de patologias cardíacas. Tais arquiteturas