Introducing topography in convolutional neural networks

1 code implementation • 28 Oct 2022 • Maxime Poli, Emmanuel Dupoux, Rachid Riad

Thus, in this work, inspired by the neuroscience literature, we proposed a new topographic inductive bias in Convolutional Neural Networks (CNNs).

Inductive Bias

Shennong: a Python toolbox for audio speech features extraction

1 code implementation • 10 Dec 2021 • Mathieu Bernard, Maxime Poli, Julien Karadayi, Emmanuel Dupoux

After describing the Shennong software architecture, its core components and implemented algorithms, this paper illustrates its use on three applications: a comparison of speech features performances on a phones discrimination task, an analysis of a Vocal Tract Length Normalization model as a function of the speech duration used for training and a comparison of pitch estimation algorithms under various noise conditions.