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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We introduce Multi-Frame Cross-Entropy training (MFCE) for convolutionalneural network acoustic models. Recognizing that similar to RNNs, CNNs are innature sequence models that take variable length inputs, we propose to take asinput to the CNN a part of an utterance long enough that multiple labels arepredicted at once, therefore getting cross-entropy loss signal from multipleadjacent frames. This increases the amount of label information drastically forsmall marginal computational cost. We show large WER improvements on hub5 andrt02 after training on the 2000-hour Switchboard benchmark.

Multi-Frame Cross-Entropy Training for Convolutional Neural Networks in Speech Recognition