Recent work has shown that it is possible to train an unsupervised
autom...
Semi-supervised learning through pseudo-labeling has become a staple of
...
SpeechBrain is an open-source and all-in-one speech toolkit. It is desig...
This paper introduces Timers and Such, a new open source dataset of spok...
Autoregressive neural network models have been used successfully for seq...
Whereas conventional spoken language understanding (SLU) systems map spe...
Keyword spotting--or wakeword detection--is an essential feature for
han...
In this paper, we introduce the syndrome loss, an alternative loss funct...
In this paper, we present a new method for recognizing tones in continuo...
The problem of low complexity, close to optimal, channel decoding of lin...