469 citations · 808 across the 29 of their papers we have counts for
9 papers · 1 filter
Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations
Cecilia Bolaños, Luciana Ferrer, Magdalena Fuentes
Correlations between events in machine learning datasets may result in shortcut learning, where models learn to predict the target event based on the presence of a correlated event…
Benchmarking Time-localized Explanations for Audio Classification Models
Cecilia Bolaños, Leonardo Pepino, Martin Meza +1
Most modern approaches for audio processing are opaque, in the sense that they do not provide an explanation for their decisions. For this reason, various methods have been propose…
The Unreliability of Acoustic Systems in Alzheimer's Speech Datasets with Heterogeneous Recording Conditions
Lara Gauder, Pablo Riera, Andrea Slachevsky +3
Automated speech analysis is a thriving approach to detect early markers of Alzheimer's disease (AD). Yet, recording conditions in most AD datasets are heterogeneous, with patients…
EnCodecMAE: Leveraging neural codecs for universal audio representation learning
Leonardo Pepino, Pablo Riera, Luciana Ferrer
The goal of universal audio representation learning is to obtain foundational models that can be used for a variety of downstream tasks involving speech, music and environmental so…
Phone and speaker spatial organization in self-supervised speech representations
Pablo Riera, Manuela Cerdeiro, Leonardo Pepino +1
Self-supervised representations of speech are currently being widely used for a large number of applications. Recently, some efforts have been made in trying to analyze the type of…
Study of positional encoding approaches for Audio Spectrogram Transformers
Leonardo Pepino, Pablo Riera, Luciana Ferrer
Transformers have revolutionized the world of deep learning, specially in the field of natural language processing. Recently, the Audio Spectrogram Transformer (AST) was proposed f…
Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings
Leonardo Pepino, Pablo Riera, Luciana Ferrer
Emotion recognition datasets are relatively small, making the use of the more sophisticated deep learning approaches challenging. In this work, we propose a transfer learning metho…
Out of a hundred trials, how many errors does your speaker verifier make?
Niko Brümmer, Luciana Ferrer, Albert Swart
Out of a hundred trials, how many errors does your speaker verifier make? For the user this is an important, practical question, but researchers and vendors typically sidestep it a…
A Speaker Verification Backend with Robust Performance across Conditions
Luciana Ferrer, Mitchell McLaren, Niko Brummer
In this paper, we address the problem of speaker verification in conditions unseen or unknown during development. A standard method for speaker verification consists of extracting…