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

Recurrent neural networks (RNN) are at the core of modern automatic speechrecognition (ASR) systems. In particular, long-short term memory (LSTM)recurrent neural networks have achieved state-of-the-art results in many speechrecognition tasks, due to their efficient representation of long and short termdependencies in sequences of inter-dependent features. Nonetheless, internaldependencies within the element composing multidimensional features are weaklyconsidered by traditional real-valued representations. We propose a novelquaternion long-short term memory (QLSTM) recurrent neural network that takesinto account both the external relations between the features composing asequence, and these internal latent structural dependencies with the quaternionalgebra. QLSTMs are compared to LSTMs during a memory copy-task and a realisticapplication of speech recognition on the Wall Street Journal (WSJ) dataset.QLSTM reaches better performances during the two experiments with up to $2.8$times less learning parameters, leading to a more expressive representation ofthe information.

Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognition