4 papers
A study on weakly-supervised training approaches for phoneme-level pronunciation scoring
Jazmín Vidal, Luciana Ferrer
Phoneme-level computer-assisted pronunciation training systems typically rely on phoneme-level annotations, which are costly and scarce. In this work, we investigate whether phonem…
ECUAS: A family of metrics for principled evaluation of uncertainty-augmented systems
Lautaro Estienne, Erik Ernst, Matías Vera +2
In high-stakes automated decision-making, access to predictive uncertainty is essential for enabling users -- human or downstream systems -- to accept or reject predictions based o…
LSCD: Lomb-Scargle Conditioned Diffusion for Time series Imputation
Elizabeth Fons, Alejandro Sztrajman, Yousef El-Laham +3
Time series with missing or irregularly sampled data are a persistent challenge in machine learning. Many methods operate on the frequency-domain, relying on the Fast Fourier Trans…
Unsupervised Calibration through Prior Adaptation for Text Classification using Large Language Models
Lautaro Estienne, Luciana Ferrer, Matías Vera +1
A wide variety of natural language tasks are currently being addressed with large-scale language models (LLMs). These models are usually trained with a very large amount of unsuper…