2 papers
cs.SD2026
Task-Vector Arithmetic for Emotional Expressivity Control in Language-Model-Based Text-to-Speech
Daniel Oliveira de Brito, Arnaldo Candido Junior
We investigate whether task-vector arithmetic, successful for cross-speaker emotional intensity control in modular text-to-speech (TTS), transfers to large-scale TTS systems built…
cs.SD2025
Fine-tuning Pre-trained Audio Models for COVID-19 Detection: A Technical Report
Daniel Oliveira de Brito, LetÃcia Gabriella de Souza, Marcelo Matheus Gauy +2
This technical report investigates the performance of pre-trained audio models on COVID-19 detection tasks using established benchmark datasets. We fine-tuned Audio-MAE and three P…