Search Results for author: Lisa van Staden

Found 2 papers, 0 papers with code

A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings

no code implementations14 Dec 2020 Lisa van Staden, Herman Kamper

We compare frame-level features from contrastive predictive coding (CPC), autoregressive predictive coding and a CAE to conventional MFCCs.

Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.