Unsupervised Learning of Semantic Audio Representations — mentioned by sdenton4

Sun, 16 Sep 2018 16:54:51 GMT

Here's the OG triplet metric learning paper: https://arxiv.org/abs/1412.6622 Their strategy is for labeled data; just take X and X' with the same labels, and Y from a different label. And here's an example of unlabeled triplet learning: https://arxiv.org/abs/1711.02209 In this case, aug(X) might be a slightly time or pitch shifted example. So whatever the label is for X, it will be the same as the label for aug(X). The advantage here is that as a framework it plays nicely with 'real' problems. Representation learning is rarely the actual problem; it's certainly not something an end-user cares…

Paper and discussion history. A mention is not an endorsement.

Unsupervised Learning of Semantic Audio Representations · HackerPapers discussions

Unsupervised Learning of Semantic Audio Representations — mentioned by sdenton4