566 citations · 2.5k across the 42 of their papers we have counts for
8 papers · 1 filter
Fully Convolutional Speech Recognition
Neil Zeghidour, Qiantong Xu, Vitaliy Liptchinsky +3
Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract me…
To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition
Yossi Adi, Neil Zeghidour, Ronan Collobert +3
Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning…
Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger
Gabriel Synnaeve, Zeming Lin, Jonas Gehring +5
We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games. We propose to…
High-Level Strategy Selection under Partial Observability in StarCraft: Brood War
Jonas Gehring, Da Ju, Vegard Mella +3
We consider the problem of high-level strategy selection in the adversarial setting of real-time strategy games from a reinforcement learning perspective, where taking an action co…
SING: Symbol-to-Instrument Neural Generator
Alexandre Défossez, Neil Zeghidour, Nicolas Usunier +2
Recent progress in deep learning for audio synthesis opens the way to models that directly produce the waveform, shifting away from the traditional paradigm of relying on vocoders…
End-to-End Speech Recognition From the Raw Waveform
Neil Zeghidour, Nicolas Usunier, Gabriel Synnaeve +2
State-of-the-art speech recognition systems rely on fixed, hand-crafted features such as mel-filterbanks to preprocess the waveform before the training pipeline. In this paper, we…
Canonical Tensor Decomposition for Knowledge Base Completion
Timothée Lacroix, Nicolas Usunier, Guillaume Obozinski
The problem of Knowledge Base Completion can be framed as a 3rd-order binary tensor completion problem. In this light, the Canonical Tensor Decomposition (CP) (Hitchcock, 1927) see…
Value Propagation Networks
Nantas Nardelli, Gabriel Synnaeve, Zeming Lin +3
We present Value Propagation (VProp), a set of parameter-efficient differentiable planning modules built on Value Iteration which can successfully be trained using reinforcement le…