4 citations · 4 across the 3 of their papers we have counts for
3 papers
On Scaling Contrastive Representations for Low-Resource Speech Recognition
Lasse Borgholt, Tycho Max Sylvester Tax, Jakob Drachmann Havtorn +2
Recent advances in self-supervised learning through contrastive training have shown that it is possible to learn a competitive speech recognition system with as little as 10 minute…
Utilizing Domain Knowledge in End-to-End Audio Processing
Tycho Max Sylvester Tax, Jose Luis Diez Antich, Hendrik Purwins +1
End-to-end neural network based approaches to audio modelling are generally outperformed by models trained on high-level data representations. In this paper we present preliminary…
Exploiting Nontrivial Connectivity for Automatic Speech Recognition
Marius Paraschiv, Lasse Borgholt, Tycho Max Sylvester Tax +2
Nontrivial connectivity has allowed the training of very deep networks by addressing the problem of vanishing gradients and offering a more efficient method of reusing parameters.…