21 citations · 154 across the 60 of their papers we have counts for
4 papers · 1 filter
A light transformer for speech-to-intent applications
Pu Wang, Hugo Van hamme
Spoken language understanding (SLU) systems can make life more agreeable, safer (e.g. in a car) or can increase the independence of physically challenged users. However, due to the…
Analysis of memory in LSTM-RNNs for source separation
Jeroen Zegers, Hugo Van hamme
Long short-term memory recurrent neural networks (LSTM-RNNs) are considered state-of-the art in many speech processing tasks. The recurrence in the network, in principle, allows an…
An LSTM Based Architecture to Relate Speech Stimulus to EEG
Mohammad Jalilpour Monesi, Bernd Accou, Jair Montoya-Martinez +2
Modeling the relationship between natural speech and a recorded electroencephalogram (EEG) helps us understand how the brain processes speech and has various applications in neuros…
Multitask Learning with Capsule Networks for Speech-to-Intent Applications
Jakob Poncelet, Hugo Van hamme
Voice controlled applications can be a great aid to society, especially for physically challenged people. However this requires robustness to all kinds of variations in speech. A s…