Lucas H. Ueda

According to our database, Lucas H. Ueda authored at least 13 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

Crab: Multi Layer Contrastive Supervision to Improve Speech Emotion Recognition Under Both Acted and Natural Speech Condition.

Lucas H. Ueda, João G. T. Lima, Paula D. P. Costa

CoRR, March, 2026

SelfTTS: cross-speaker style transfer through explicit embedding disentanglement and self-refinement using self-augmentation.

Lucas H. Ueda, João Lima, Pedro Corrêa, Flávio Olmos Simões, Mário Uliani Neto, Paula D. P. Costa

CoRR, March, 2026

2025

Evaluating Emotion Recognition in Spoken Language Models on Emotionally Incongruent Speech.

Pedro Corrêa, João Lima, Victor Moreno, Lucas H. Ueda, Paula Dornhofer Paro Costa

CoRR, October, 2025

Emotionally Incongruent Synthetic Speech Dataset (EMIS).

Pedro Corrêa, João Lima, Victor Moreno, Lucas H. Ueda, Paula D. P. Costa

Dataset, September, 2025

Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking Model.

Lucas H. Ueda, João Lima, Leonardo Marques, Paula Dornhofer Paro Costa

Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025

2024

Exploring synthetic data for cross-speaker style transfer in style representation based TTS.

Lucas H. Ueda, Leonardo B. de M. M. Marques, Flávio Olmos Simões, Mário Uliani Neto, Fernando O. Runstein, Bianca Dal Bó, Paula D. P. Costa

CoRR, 2024

Gesture Area Coverage to Assess Gesture Expressiveness and Human-Likeness.

Rodolfo Luis Tonoli, Paula Dornhofer Paro Costa, Leonardo Boulitreau de Menezes Martins Marques, Lucas Hideki Ueda

Proceedings of the Companion Proceedings of the 26th International Conference on Multimodal Interaction, 2024

Vision Transformer MST++: Efficient Hyperspectral Skin Reconstruction.

Ana Clara Caznok Silveira, Diedre Santos do Carmo, Lucas H. Ueda, Denis G. Fantinato, Paula D. P. Costa, Letícia Rittner

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

Spectro-ViT: A Vision Transformer Model for GABA-edited MRS Reconstruction Using Spectrograms.

Gabriel Santos Martins Dias, Rodrigo Pommot Berto, Mateus Oliveira, Lucas H. Ueda, Sergio Dertkigil, Paula D. P. Costa, Amirmohammad Shamaei, Roberto Souza, Ashley D. Harris, Letícia Rittner

CoRR, 2023

Gesture Generation with Diffusion Models Aided by Speech Activity Information.

Rodolfo L. Tonoli, Leonardo B. de M. M. Marques, Lucas H. Ueda, Paula Dornhofer Paro Costa

Proceedings of the International Conference on Multimodal Interaction, 2023

2022

Diffusion-Based Approach to Style Modeling in Expressive TTS.

Leonardo B. de M. M. Marques, Lucas H. Ueda, Flávio Olmos Simões, Mário Uliani Neto, Fernando O. Runstein, Edson Jose Nagle, Bianca Dal Bó, Paula D. P. Costa

Proceedings of the Intelligent Systems - 11th Brazilian Conference, 2022

2021

Are we truly modeling expressiveness? A study on expressive TTS in Brazilian Portuguese for real-life application styles.

Lucas H. Ueda, Paula D. P. Costa, Flávio Olmos Simões, Mário Uliani Neto

Proceedings of the 11th ISCA Speech Synthesis Workshop, 2021

The CPQD-Unicamp system for Blizzard Challenge 2021.

Mário Uliani Neto, Flávio Olmos Simões, Fernando O. Runstein, Edson Jose Nagle, Bianca Dal Bó, Lucas H. Ueda, Paula D. P. Costa

Proceedings of the Blizzard Challenge 2021, virtual, October 23, 2021, 2021