From the 1 of 9 linked papers with an AI index.
9 papers
CARE: A Multimodal Corpus for Studying Speech and Non-Verbal Communication Across Multiple Medical Conditions
David Gimeno-Gómez, Catarina Botelho, Carlos-D. MartÃnez-Hinarejos +2
The paper introduces CARE v1.0, a curated multimodal English dataset of about 144 hours of short video interviews from 612 participants covering 12 medical conditions and a control…
ESPnet3: Infrastructure for Scalable Speech and Audio Research in the Foundation Model Era
Masao Someki, Alexander Polok, Carlos Carvalho +14
Recent speech research involves increasingly large datasets, complex models, and diverse experimental workflows. However, existing frameworks require substantial engineering effort…
Rethinking Depth: A study of the Recursive-Transformer for Speech Recognition
Thomas Rolland, Carlos Carvalho, Alberto Abad
Transformer-based architectures have led to significant improvements in Automatic Speech Recognition (ASR), often at the cost of substantially increased model sizes. A promising ap…
FalAR: A Large-scale Speaker-Annotated European Portuguese Speech Corpus of Parliamentary Sessions
Francisco Teixeira, Carlos Carvalho, Mariana Julião +7
State-of-the-art performance for Automatic Speech Recognition (ASR) largely depends on the availability of large-scale labeled corpora. This creates a demand for increased data col…
Evaluating Parkinson's Disease Detection in Anonymized Speech: A Performance and Acoustic Analysis
Carlos Franzreb, Francisco Teixeira, Ben Luks +2
Automatic detection of Parkinson's disease (PD) from speech is a promising non-invasive diagnostic tool, but it raises significant privacy concerns. Speaker anonymization mitigates…
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…