Sign in

Augmentation adversarial training for unsupervised speaker recognition

By Jaesung Huh and others
The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be similar and across-utterance embeddings to be dissimilar. However, since the within-utterance segments share the same acoustic... Show more
August 9, 2020
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Augmentation adversarial training for unsupervised speaker recognition
Click on play to start listening