1 code implementation • 22 May 2022 • Fayçal Aït Aoudia, Jakob Hoydis, Sebastian Cammerer, Matthijs Van Keirsbilck, Alexander Keller
We propose a neural network (NN)-based algorithm for device detection and time of arrival (ToA) and carrier frequency offset (CFO) estimation for the narrowband physical random-access channel (NPRACH) of narrowband internet of things (NB-IoT).
no code implementations • 31 Mar 2021 • Gonçalo Mordido, Matthijs Van Keirsbilck, Alexander Keller
We demonstrate that 1x1-convolutions in 1D time-channel separable convolutions may be replaced by constant, sparse random ternary matrices with weights in $\{-1, 0,+1\}$.
no code implementations • 5 Mar 2021 • Alexander Keller, Matthijs Van Keirsbilck
Artificial neural networks can be represented by paths.
no code implementations • 29 May 2019 • Gonçalo Mordido, Matthijs Van Keirsbilck, Alexander Keller
Low bit-width integer weights and activations are very important for efficient inference, especially with respect to lower power consumption.
no code implementations • 29 May 2019 • Matthijs Van Keirsbilck, Alexander Keller, Xiaodong Yang
We study structurally sparse RNNs, showing that they are well suited for acceleration on parallel hardware, with a greatly reduced cost of the recurrent operations as well as orders of magnitude less recurrent weights.
no code implementations • 13 Mar 2018 • Matthijs Van keirsbilck, Bert Moons, Marian Verhelst
Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video simultaneously - significantly enhances the performance of such systems, especially in noisy environments.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3