1 citations · 1 across the 6 of their papers we have counts for
7 papers
Radiative Data for As III, Se III, Hf IV, and Tl IV: HFR and MCDHF Calculations for Hot Subdwarf Spectroscopy
Jérôme Deprince, Lucas Maison, Solène Beauraind +3
Accurate oscillator strengths for doubly and triply ionised heavy elements are required for quantitative spectroscopy of hot subdwarfs, but available data remain sparse. We present…
Benchmarking the Plane-Wave Born and Distorted Waves approximations for electron-impact collision strength computations: the sample case of Sr II
Jérôme Deprince, Lucas Maison
The discovery of gravitational waves from a neutron star merger in 2017 (GW170817) and the associated kilonova (AT2017gfo) confirmed these events as key sites for heavy element pro…
Evaluating and Improving the Robustness of Speech Command Recognition Models to Noise and Distribution Shifts
Anaïs Baranger, Lucas Maison
Although prior work in computer vision has shown strong correlations between in-distribution (ID) and out-of-distribution (OOD) accuracies, such relationships remain underexplored…
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…
Compression of Recurrent Neural Networks using Matrix Factorization
Lucas Maison, Hélion du Mas des Bourboux, Thomas Courtat
Compressing neural networks is a key step when deploying models for real-time or embedded applications. Factorizing the model's matrices using low-rank approximations is a promisin…
Some voices are too common: Building fair speech recognition systems using the Common Voice dataset
Lucas Maison, Yannick Estève
Automatic speech recognition (ASR) systems become increasingly efficient thanks to new advances in neural network training like self-supervised learning. However, they are known to…
Improving Accented Speech Recognition with Multi-Domain Training
Lucas Maison, Yannick Estève
Thanks to the rise of self-supervised learning, automatic speech recognition (ASR) systems now achieve near-human performance on a wide variety of datasets. However, they still lac…