collaborators

6 papers

cs.CL2026

Speaker Group Encoding in Self-supervised Speech Recognition Models

Felix Herron, Solange Rossato Alexandre Allauzen, Benoit Favre +1

We investigate what self-supervised speech recognition models (S3Ms) learn about speaker groups (SGs). We examine several states of S3Ms: pretrained, finetuned on speaker identific…

cs.CL2026

Responsible Benchmarking of Fairness for Automatic Speech Recognition

Felix Herron, Ange Richard, François Portet +2

Many studies have shown automatic speech processing (ASR) systems have unequal performance across speakergroups (SG's). However, the manner in which such studies arrive at this con…

cs.CL2026

Identifying and typifying demographic unfairness in phoneme-level embeddings of self-supervised speech recognition models

Felix Herron, Solange Rossato, Alexandre Allauzen +1

Modern automatic speech recognition (ASR) systems have been observed to function better for certain speaker groups (SGs) than others, despite recent gains in overall performance. O…

cs.CL2026

Where Do Self-Supervised Speech Models Become Unfair?

Felix Herron, Maja Hjuler, Solange Rossato +2

Speech encoder models are known to model members of some speaker groups (SGs) better than others. However, there has been little work in establishing why this occurs on a technolog…

cs.CL2026

Polynomial Mixing for Efficient Self-supervised Speech Encoders

Eva Feillet, Ryan Whetten, David Picard +1

State-of-the-art speech-to-text models typically employ Transformer-based encoders that model token dependencies via self-attention mechanisms. However, the quadratic complexity of…

cs.CL2025

Interference Matrix: Quantifying Cross-Lingual Interference in Transformer Encoders

Belen Alastruey, João Maria Janeiro, Alexandre Allauzen +3

In this paper, we present a comprehensive study of language interference in encoder-only Transformer models across 83 languages. We construct an interference matrix by training and…