English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Wav2vec-C introduces a novel representation learning technique combiningelements from wav2vec 2.0 and VQ-VAE. Our model learns to reproduce quantizedrepresentations from partially masked speech encoding using a contrastive lossin a way similar to Wav2vec 2.0. However, the quantization process isregularized by an additional consistency network that learns to reconstruct theinput features to the wav2vec 2.0 network from the quantized representations ina way similar to a VQ-VAE model. The proposed self-supervised model is trainedon 10k hours of unlabeled data and subsequently used as the speech encoder in aRNN-T ASR model and fine-tuned with 1k hours of labeled data. This work is oneof only a few studies of self-supervised learning on speech tasks with a largevolume of real far-field labeled data. The Wav2vec-C encoded representationsachieves, on average, twice the error reduction over baseline and a highercodebook utilization in comparison to wav2vec 2.0

Wav2vec-C: A Self-supervised Model for Speech Representation Learning