← Search

Jakob D. Havtorn

2 accepted papers

2021

Hierarchical VAEs Know What They Don’t Know

ICML 2021spotlight

Deep generative models have been demonstrated as state-of-the-art density estimators. Yet, recent work has found that they often assign a higher likelihood to data from outside the training distribution. This seemingly paradoxical behavior has caused concerns over the quality of the attained density…

2021

On Scaling Contrastive Representations for Low-Resource Speech Recognition

ICASSP 2021accepted

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 minutes of labeled data. However, these systems are computationally expensive since they require pre-training followed by fine…

Cited by 0SourceScholar