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

Long Short Term Memory Connectionist Temporal Classification (LSTM-CTC) basedend-to-end models are widely used in speech recognition due to its simplicityin training and efficiency in decoding. In conventional LSTM-CTC based models,a bottleneck projection matrix maps the hidden feature vectors obtained fromLSTM to softmax output layer. In this paper, we propose to use a high rankprojection layer to replace the projection matrix. The output from the highrank projection layer is a weighted combination of vectors that are projectedfrom the hidden feature vectors via different projection matrices andnon-linear activation function. The high rank projection layer is able toimprove the expressiveness of LSTM-CTC models. The experimental results showthat on Wall Street Journal (WSJ) corpus and LibriSpeech data set, the proposedmethod achieves 4%-6% relative word error rate (WER) reduction over thebaseline CTC system. They outperform other published CTC based end-to-end (E2E)models under the condition that no external data or data augmentation isapplied. Code has been made available at https://github.com/mobvoi/lstm_ctc.

End-To-End Speech Recognition Using A High Rank LSTM-CTC Based Model