1.1k citations · 3.3k across the 89 of their papers we have counts for
Showing 2017 · cs.CLShow all
2 papers · 2 filters
cs.CL2017
Letter-Based Speech Recognition with Gated ConvNets
Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert
In the recent literature, "end-to-end" speech systems often refer to letter-based acoustic models trained in a sequence-to-sequence manner, either via a recurrent model or via a st…
cs.CL2017
Learning Filterbanks from Raw Speech for Phone Recognition
Neil Zeghidour, Nicolas Usunier, Iasonas Kokkinos +3
We train a bank of complex filters that operates on the raw waveform and is fed into a convolutional neural network for end-to-end phone recognition. These time-domain filterbanks…