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

We present a system for the Zero Resource Speech Challenge 2021, whichcombines a Contrastive Predictive Coding (CPC) with deep cluster. In deepcluster, we first prepare pseudo-labels obtained by clustering the outputs of aCPC network with k-means. Then, we train an additional autoregressive model toclassify the previously obtained pseudo-labels in a supervised manner. Phonemediscriminative representation is achieved by executing the second-roundclustering with the outputs of the final layer of the autoregressive model. Weshow that replacing a Transformer layer with a Conformer layer leads to afurther gain in a lexical metric. Experimental results show that a relativeimprovement of 35% in a phonetic metric, 1.5% in the lexical metric, and 2.3%in a syntactic metric are achieved compared to a baseline method of CPC-smallwhich is trained on LibriSpeech 460h data. We achieve top results in thischallenge with the syntactic metric.

Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021