3 papers
cs.CL2026
Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASR
Carlos Carvalho, Francisco Teixeira, Thomas Rolland +1
Model merging is a scalable alternative to multi-task training that combines the capabilities of multiple specialised models into a single model. This is particularly attractive fo…
cs.CL2025
CAMÃES: A Comprehensive Automatic Speech Recognition Benchmark for European Portuguese
Carlos Carvalho, Francisco Teixeira, Catarina Botelho +9
Existing resources for Automatic Speech Recognition in Portuguese are mostly focused on Brazilian Portuguese, leaving European Portuguese (EP) and other varieties under-explored. T…
eess.AS2024
AC-Mix: Self-Supervised Adaptation for Low-Resource Automatic Speech Recognition using Agnostic Contrastive Mixup
Carlos Carvalho, Alberto Abad
Self-supervised learning (SSL) leverages large amounts of unlabelled data to learn rich speech representations, fostering improvements in automatic speech recognition (ASR), even w…