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

In this paper, we investigate the benefit that off-the-shelf word embeddingcan bring to the sequence-to-sequence (seq-to-seq) automatic speech recognition(ASR). We first introduced the word embedding regularization by maximizing thecosine similarity between a transformed decoder feature and the target wordembedding. Based on the regularized decoder, we further proposed the fuseddecoding mechanism. This allows the decoder to consider the semanticconsistency during decoding by absorbing the information carried by thetransformed decoder feature, which is learned to be close to the target wordembedding. Initial results on LibriSpeech demonstrated that pre-trained wordembedding can significantly lower ASR recognition error with a negligible cost,and the choice of word embedding algorithms among Skip-gram, CBOW and BERT isimportant.

Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding