5 papers
A Study of Data Selection Strategies for Pre-training Self-Supervised Speech Models
Ryan Whetten, Titouan Parcollet, Marco Dinarelli +1
Self-supervised learning (SSL) has transformed speech processing, yet its reliance on massive pre-training datasets remains a bottleneck. While robustness is often attributed to sc…
Ara-Best-RQ: Multi Dialectal Arabic SSL
Haroun Elleuch, Ryan Whetten, Salima Mdhaffar +2
We present Ara-BEST-RQ, a family of self-supervised learning (SSL) models specifically designed for multi-dialectal Arabic speech processing. Leveraging 5,640 hours of crawled Crea…
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…
In-domain SSL pre-training and streaming ASR
Jarod Duret, Salima Mdhaffar, Gaëlle Laperrière +6
In this study, we investigate the benefits of domain-specific self-supervised pre-training for both offline and streaming ASR in Air Traffic Control (ATC) environments. We train BE…
Towards Early Prediction of Self-Supervised Speech Model Performance
Ryan Whetten, Lucas Maison, Titouan Parcollet +2
In Self-Supervised Learning (SSL), pre-training and evaluation are resource intensive. In the speech domain, current indicators of the quality of SSL models during pre-training, su…